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

    Neuronpedia

    INDEX
    Explanations

    special characters or formatting in the text

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

    language continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Carriera
    -0.57
    windowFixed
    -0.54
    Carto
    -0.53
    JAKARTA
    -0.52
    rawQuery
    -0.49
    ylvan
    -0.48
    ksam
    -0.48
    Amaz
    -0.48
    Exposure
    -0.47
    Cristo
    -0.46
    POSITIVE LOGITS
    __(/*!
    0.44
    ことになる
    0.44
     thus
    0.43
    enumi
    0.39
     Infórmanos
    0.38
     bandeira
    0.36
     mijne
    0.36
     rodzaju
    0.35
     aranha
    0.35
     morrer
    0.35
    Act Density 0.000%

    No Known Activations