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

    Neuronpedia

    INDEX
    Explanations

    located

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sleep
    -0.06
    364
    -0.06
    _my
    -0.06
     defaultProps
    -0.06
    ons
    -0.06
     detalles
    -0.06
    Listeners
    -0.06
    _tl
    -0.06
    fef
    -0.06
     nv
    -0.06
    POSITIVE LOGITS
    521
    0.07
     scattering
    0.07
     Alexandre
    0.07
     esas
    0.07
    _DAC
    0.06
     intrusion
    0.06
    ива
    0.06
    構
    0.06
     Est
    0.06
    Ο
    0.06
    Act Density 0.002%

    No Known Activations