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

    Neuronpedia

    INDEX
    Explanations

    explanation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     device
    -0.07
    Der
    -0.07
     Zones
    -0.07
     Device
    -0.07
     servants
    -0.07
     Construct
    -0.06
    Des
    -0.06
     grandi
    -0.06
    /controller
    -0.06
     devices
    -0.06
    POSITIVE LOGITS
    prus
    0.07
    091
    0.06
    _SOL
    0.06
     밀
    0.06
    .vs
    0.06
     Paula
    0.06
    Từ
    0.06
     جی
    0.06
    reau
    0.06
    �프
    0.06
    Act Density 0.005%

    No Known Activations