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

    Neuronpedia

    INDEX
    Explanations

    slave

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     armor
    -0.07
     Morrison
    -0.07
     junction
    -0.07
    enticator
    -0.07
     diversion
    -0.07
    州市
    -0.07
     reiterated
    -0.07
    ecedor
    -0.07
    팅
    -0.06
     spectrum
    -0.06
    POSITIVE LOGITS
     Slave
    0.07
    alc
    0.07
     slaves
    0.07
     Qty
    0.07
     slave
    0.06
    BY
    0.06
     DOM
    0.06
    krv
    0.06
    apel
    0.06
    хи
    0.06
    Act Density 0.009%

    No Known Activations