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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rd
    -0.08
     налич
    -0.07
    光荣
    -0.07
    '>"+
    -0.07
    实际
    -0.07
     свое
    -0.07
    _bc
    -0.06
    adget
    -0.06
    .REG
    -0.06
    (fig
    -0.06
    POSITIVE LOGITS
    we
    0.07
    weigh
    0.07
    /payment
    0.07
    iw
    0.07
     היחיד
    0.06
     Myers
    0.06
    ┲
    0.06
    speech
    0.06
    orough
    0.06
    ban
    0.06
    Act Density 0.003%

    No Known Activations