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

    Neuronpedia

    INDEX
    Explanations

    ks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arrera
    -0.07
    (prop
    -0.07
    enders
    -0.07
    име
    -0.06
     desarrollo
    -0.06
     fondo
    -0.06
     excluded
    -0.06
    림
    -0.06
    (pm
    -0.06
     heroes
    -0.06
    POSITIVE LOGITS
    Offsets
    0.07
    .timing
    0.06
    .frequency
    0.06
    frequency
    0.06
    RARY
    0.06
    Reaction
    0.05
    _gc
    0.05
     guest
    0.05
     мат
    0.05
    MT
    0.05
    Act Density 0.138%

    No Known Activations