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

    Neuronpedia

    INDEX
    Explanations

    synchronized

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BN
    -0.07
    River
    -0.06
    bara
    -0.06
    going
    -0.06
     Jac
    -0.06
    виг
    -0.06
    IFF
    -0.06
    bitrary
    -0.06
     curso
    -0.06
     ав
    -0.06
    POSITIVE LOGITS
     Scandin
    0.07
     setIs
    0.06
     Derrick
    0.06
     nervous
    0.06
     safeguard
    0.06
    _chan
    0.06
    _DISTANCE
    0.06
     suspicions
    0.06
    .Memory
    0.06
    loub
    0.06
    Act Density 0.001%

    No Known Activations