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

    Neuronpedia

    INDEX
    Explanations

    identity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поруш
    -0.07
    _VF
    -0.06
    281
    -0.06
    χής
    -0.06
    نى
    -0.06
    .gz
    -0.06
    _Final
    -0.06
     Std
    -0.06
    +B
    -0.06
     ber
    -0.06
    POSITIVE LOGITS
    cod
    0.07
     species
    0.07
    car
    0.06
     calendar
    0.06
    ogenous
    0.06
    (square
    0.06
     sovereignty
    0.06
     decorator
    0.06
    preview
    0.06
     identify
    0.06
    Act Density 0.021%

    No Known Activations