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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "back" indicating references to returning or responding in conversations

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

    response or return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.49
     líquida
    -0.36
    IsMutable
    -0.34
     líqu
    -0.34
    *************/
    -0.32
     líquido
    -0.31
    djangoproject
    -0.31
     ModelRenderer
    -0.31
     JSONArray
    -0.31
     nakalista
    -0.31
    POSITIVE LOGITS
     كومونز
    0.66
     Back
    0.57
    Back
    0.56
    RenderAtEndOf
    0.54
    BACK
    0.53
    gamesh
    0.52
     BACK
    0.51
     feedback
    0.51
    Terug
    0.51
     back
    0.50
    Act Density 0.016%

    No Known Activations