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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nut
    -0.08
    وت
    -0.07
     เ�
    -0.07
    _PROF
    -0.07
     Ahmed
    -0.07
    icol
    -0.07
    /widgets
    -0.07
    .spring
    -0.07
     Cove
    -0.07
    _compat
    -0.07
    POSITIVE LOGITS
     ^{°}
    0.07
     Perl
    0.06
    怎么
    0.06
     detections
    0.06
     dijital
    0.06
     MMI
    0.05
    �m
    0.05
    Transformation
    0.05
     :)↵
    0.05
    erra
    0.05
    Act Density 0.268%

    No Known Activations