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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acb
    -0.06
     vivo
    -0.06
    USB
    -0.06
     landmarks
    -0.06
     skal
    -0.06
     forfeiture
    -0.06
    Ellipse
    -0.06
     Bak
    -0.06
     Kelley
    -0.06
     shave
    -0.06
    POSITIVE LOGITS
    _interrupt
    0.08
    ес
    0.07
     reflex
    0.06
     im
    0.06
    Contracts
    0.06
    (Response
    0.06
    季
    0.06
     emitter
    0.06
     compares
    0.06
    募
    0.06
    Act Density 0.006%

    No Known Activations