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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and identifiers

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

    Vanessa or similar names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     morts
    -0.40
     Genehmigung
    -0.39
     if
    -0.36
    यु
    -0.35
    print
    -0.34
    ckså
    -0.33
    light
    -0.32
    APPRO
    -0.32
    leyeb
    -0.32
    DAB
    -0.32
    POSITIVE LOGITS
     Vanessa
    2.16
    Vanessa
    1.98
    essa
    0.82
    ESSA
    0.77
     vane
    0.75
     Ness
    0.75
     myſelf
    0.71
    InjectAttribute
    0.69
     Tessa
    0.69
     uLocal
    0.68
    Act Density 0.002%

    No Known Activations