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

    Neuronpedia

    INDEX
    Explanations

    references to common elements or components in various contexts

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

    common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.68
     ModelExpression
    -0.63
    httphttps
    -0.59
    SequentialGroup
    -0.56
    ագրություններ
    -0.53
    MethodManager
    -0.52
    Filmographie
    -0.51
     tartalomajánló
    -0.50
     psycopg
    -0.50
    ConstraintMaker
    -0.50
    POSITIVE LOGITS
    common
    1.26
     common
    1.02
    Common
    0.96
     Common
    0.85
    COMMON
    0.85
     COMMON
    0.81
     comunes
    0.81
     CommonModule
    0.78
    CommonModule
    0.75
     común
    0.73
    Act Density 0.005%

    No Known Activations