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

    Neuronpedia

    INDEX
    Explanations

    inquiries concerning conditional statements or considerations

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

    asking about a possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PSC
    -0.55
    IMC
    -0.54
     Palis
    -0.54
     Danilo
    -0.53
     VD
    -0.53
     PRD
    -0.53
    XG
    -0.52
     Mante
    -0.52
     GD
    -0.51
     Sanford
    -0.51
    POSITIVE LOGITS
     WHETHER
    1.09
     whether
    1.01
    whether
    1.00
    Whether
    0.83
     Whether
    0.79
     jestli
    0.78
     apakah
    0.65
     Apakah
    0.62
    jalá
    0.61
    eramente
    0.60
    Act Density 0.020%

    No Known Activations