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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nakonec
    -0.07
    Tok
    -0.07
    _MUT
    -0.06
    .Context
    -0.06
     živ
    -0.06
    .Consumer
    -0.06
    .Done
    -0.06
    Mut
    -0.06
    HeaderValue
    -0.06
    mam
    -0.06
    POSITIVE LOGITS
     surprises
    0.07
    .catalog
    0.07
    sti
    0.07
    ihat
    0.07
     truths
    0.07
    -ranging
    0.06
    having
    0.06
    เศรษฐ
    0.06
    .Normalize
    0.06
     capacitor
    0.06
    Act Density 0.002%

    No Known Activations