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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grabs
    -0.07
    Happy
    -0.06
    라인
    -0.06
    .write
    -0.06
    !\
    -0.06
     establish
    -0.06
    time
    -0.06
     Saints
    -0.06
    hour
    -0.06
     Distance
    -0.06
    POSITIVE LOGITS
     Gew
    0.07
     Adobe
    0.07
    XL
    0.07
     léč
    0.06
     Tes
    0.06
     лекар
    0.06
     ženy
    0.06
    ED
    0.06
    uzey
    0.06
     searchable
    0.06
    Act Density 0.070%

    No Known Activations