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

    Neuronpedia

    INDEX
    Explanations

    Random online platform messages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _almost
    -0.07
    נוח
    -0.07
    Attempt
    -0.07
    服
    -0.07
    迟到
    -0.07
    _Init
    -0.07
    тр
    -0.07
     Hairst
    -0.07
    뎅
    -0.07
     they
    -0.07
    POSITIVE LOGITS
    后台
    0.07
     데이터
    0.07
    因而
    0.07
     Curve
    0.07
    (Roles
    0.07
     Remarks
    0.07
     Parliamentary
    0.07
    .Requires
    0.07
     yür
    0.07
     ayrıl
    0.07
    Act Density 0.036%

    No Known Activations