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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially commas and conjunctions

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

    engaging, efficient, optimal descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    -0.53
    itself
    -0.51
     enfans
    -0.45
    jenost
    -0.44
     Bren
    -0.43
     initComponents
    -0.43
    usermodel
    -0.42
    GEBURTSDATUM
    -0.42
    shr
    -0.41
     partnership
    -0.41
    POSITIVE LOGITS
     solutions
    0.60
     proposals
    0.56
     MediatR
    0.56
    Diweddarwch
    0.49
    bewerken
    0.49
     Lösungen
    0.48
     descriptions
    0.48
     applications
    0.47
     lavable
    0.46
     performances
    0.45
    Act Density 0.022%

    No Known Activations