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

    Neuronpedia

    INDEX
    Explanations

    low power, dark current

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     palk
    -0.09
     scenic
    -0.08
     Govt
    -0.08
    ugc
    -0.08
    anych
    -0.08
     ضلع
    -0.08
     policym
    -0.08
     формате
    -0.08
     decorar
    -0.08
     նկար
    -0.08
    POSITIVE LOGITS
    Dark
    0.09
     dark
    0.08
     Dark
    0.08
     Leakage
    0.08
     negligible
    0.08
    dark
    0.08
    Idle
    0.07
     Creek
    0.07
     leakage
    0.07
    流水
    0.07
    Act Density 0.009%

    No Known Activations