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
     WebSocket
    -0.07
     sickness
    -0.06
     nhỏ
    -0.06
    isation
    -0.06
     cavity
    -0.06
     referrals
    -0.06
    (_.
    -0.06
     ballistic
    -0.06
    assa
    -0.06
    olla
    -0.06
    POSITIVE LOGITS
     произ
    0.16
     преп
    0.15
     형
    0.09
    нообраз
    0.08
     일
    0.08
    iflower
    0.08
     уси
    0.07
    μπ
    0.06
     sprinkle
    0.06
     crib
    0.06
    Act Density 0.002%

    No Known Activations