Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate emotional responses or interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after prepositions "with," "about," "to"

    np_acts-logits-general · gemini-2.0-flash

    students or learners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageOf
    -0.84
     ModelExpression
    -0.75
    ModelAdmin
    -0.72
     BoxDecoration
    -0.69
     BrowserModule
    -0.64
    
    -0.64
    setVerticalGroup
    -0.63
     bosses
    -0.63
    UnitTesting
    -0.63
    ("}");
    -0.62
    POSITIVE LOGITS
     Diakses
    0.51
     Roskov
    0.50
     kids
    0.47
     student
    0.47
     students
    0.46
     studenten
    0.46
    tudiant
    0.45
     cháu
    0.45
     murid
    0.45
    articulo
    0.44
    Act Density 2.793%

    No Known Activations