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

    Neuronpedia

    INDEX
    Explanations

    business reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    valuation
    -0.07
    .rawQuery
    -0.07
    buch
    -0.07
     tweets
    -0.07
     nostalgic
    -0.07
    ɾ
    -0.07
    <hr
    -0.06
    ㅆ
    -0.06
     nud
    -0.06
    /post
    -0.06
    POSITIVE LOGITS
     ue
    0.08
    XE
    0.07
     Spaces
    0.07
    ㅔ
    0.07
    ´
    0.07
    的那种
    0.07
    FE
    0.07
    sse
    0.07
    .Box
    0.07
     scares
    0.07
    Act Density 0.000%

    No Known Activations