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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and personal interactions

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

    response fausse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exploration
    -0.38
    Exploration
    -0.36
    awtextra
    -0.34
     resourceCulture
    -0.33
     Exploration
    -0.33
    ItemLayout
    -0.33
    UseVisualStyle
    -0.32
    exploration
    -0.32
    hilangan
    -0.31
    mag
    -0.30
    POSITIVE LOGITS
    jago
    0.50
     positively
    0.50
    stateProvider
    0.49
    oaks
    0.47
     positif
    0.47
    LookAnd
    0.47
    createObject
    0.46
    InputTagHelper
    0.46
     alça
    0.46
    ⟬
    0.45
    Act Density 0.387%

    No Known Activations