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

    Neuronpedia

    INDEX
    Explanations

    Boost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amb
    -0.08
     funny
    -0.07
     Decide
    -0.07
    Fund
    -0.06
    Friend
    -0.06
    JsonProperty
    -0.06
     pilot
    -0.06
     FIN
    -0.06
     Edwin
    -0.06
    _IMPL
    -0.06
    POSITIVE LOGITS
    累
    0.06
     منها
    0.06
     منه
    0.06
    riers
    0.06
    utting
    0.06
     greatness
    0.06
     unimagin
    0.06
     tome
    0.06
     witnessing
    0.06
    rection
    0.06
    Act Density 0.002%

    No Known Activations