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

    Neuronpedia

    INDEX
    Explanations

    fat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Human
    -0.06
     unacceptable
    -0.06
     Hulk
    -0.06
    _edge
    -0.06
    ments
    -0.06
     warrant
    -0.06
     polynomial
    -0.06
     Dead
    -0.06
     Commod
    -0.06
     temperatures
    -0.06
    POSITIVE LOGITS
    keterangan
    0.07
    шибка
    0.06
    OME
    0.06
    =True
    0.06
     �
    0.06
    Span
    0.06
    eguard
    0.06
    orsch
    0.06
     TJ
    0.06
    15
    0.06
    Act Density 0.011%

    No Known Activations