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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey conditional or consequential relationships

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

    that clauses defining capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gewel
    -0.44
     pesada
    -0.42
     entry
    -0.41
     uttered
    -0.41
    licherweise
    -0.41
    Autom
    -0.40
     imprensa
    -0.40
     indicator
    -0.40
    countDown
    -0.40
    omation
    -0.39
    POSITIVE LOGITS
    ⟬
    0.52
    yntaxException
    0.52
    IndentedString
    0.51
    IntoConstraints
    0.49
    AndroidJUnit
    0.47
     sustainable
    0.47
     ExecuteAsync
    0.46
    цездатний
    0.46
    Geplaatst
    0.45
     möglichst
    0.45
    Act Density 0.058%

    No Known Activations