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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [maxn
    -0.07
     Verb
    -0.06
     fas
    -0.06
     lineback
    -0.06
    -"
    -0.06
     Occ
    -0.06
    fen
    -0.06
    xEB
    -0.06
     Surveillance
    -0.06
     Lords
    -0.06
    POSITIVE LOGITS
    μένες
    0.07
     ere
    0.06
    _can
    0.06
     renk
    0.06
    权限
    0.06
     kart
    0.06
    락
    0.06
    งก
    0.06
     zarar
    0.06
    _DAY
    0.06
    Act Density 0.001%

    No Known Activations