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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nep
    -0.07
    (chunk
    -0.07
     status
    -0.06
     tribute
    -0.06
    hr
    -0.06
    -post
    -0.06
    .LogWarning
    -0.06
    _component
    -0.06
    ίζ
    -0.06
    中的
    -0.06
    POSITIVE LOGITS
     JA
    0.07
    arranty
    0.06
     غير
    0.06
    .utf
    0.06
     Hoe
    0.06
     Wrestle
    0.06
     Πο
    0.06
     TZ
    0.06
     @"↵
    0.06
    IFn
    0.06
    Act Density 0.042%

    No Known Activations