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

    Neuronpedia

    INDEX
    Explanations

    signal power

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Method
    -0.07
     twisting
    -0.07
    觀
    -0.07
    _arrays
    -0.06
    _SWITCH
    -0.06
    leyen
    -0.06
    Buff
    -0.06
     kodu
    -0.06
    ывает
    -0.06
    —
    -0.06
    POSITIVE LOGITS
     Fence
    0.07
     noqa
    0.06
    .blob
    0.06
     Customize
    0.06
     anymore
    0.06
     Hispan
    0.06
    -thumb
    0.06
     ypos
    0.06
    ープ
    0.06
    位於
    0.06
    Act Density 0.065%

    No Known Activations