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

    Neuronpedia

    INDEX
    Explanations

    code, data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.77
    piram
    -0.71
     purpoſe
    -0.68
    dafx
    -0.64
     Sarm
    -0.62
     فريبيس
    -0.61
    ualaikum
    -0.60
     виправивши
    -0.59
    ſelves
    -0.59
     Riproduzione
    -0.59
    POSITIVE LOGITS
     havoc
    0.53
     of
    0.50
     ha
    0.47
    Obituary
    0.44
    enius
    0.41
    Sinon
    0.40
    archiviato
    0.40
    チュ
    0.40
     nope
    0.40
    DDE
    0.40
    Act Density 0.000%

    No Known Activations