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

    Neuronpedia

    INDEX
    Explanations

    Publicity and news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .functions
    -0.08
    พล
    -0.07
     количе
    -0.07
     Laser
    -0.07
     verbose
    -0.06
     Mountain
    -0.06
    _any
    -0.06
     sensors
    -0.06
     Analyzer
    -0.06
     Height
    -0.06
    POSITIVE LOGITS
    ині
    0.07
    �
    0.06
    ��
    0.06
     erotica
    0.06
    599
    0.06
     karak
    0.06
     subsidi
    0.06
    uc
    0.06
     gratuito
    0.06
    _flux
    0.06
    Act Density 0.134%

    No Known Activations