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

    Neuronpedia

    INDEX
    Explanations

    -A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibly
    -0.07
    .hm
    -0.07
     rápido
    -0.07
    lič
    -0.06
     Above
    -0.06
    /rs
    -0.06
    -Feb
    -0.06
     convergence
    -0.06
    .NonNull
    -0.06
    meno
    -0.06
    POSITIVE LOGITS
    -A
    0.07
     dispose
    0.07
    ReuseIdentifier
    0.06
     Pend
    0.06
     граждан
    0.06
     MOZ
    0.06
    *time
    0.06
    .model
    0.06
     neut
    0.06
    _COLS
    0.06
    Act Density 0.001%

    No Known Activations