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

    Neuronpedia

    INDEX
    Explanations

    descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pulse
    -0.07
    /address
    -0.07
     col
    -0.06
    /utility
    -0.06
    Jak
    -0.06
    ocols
    -0.06
    (es
    -0.06
    =com
    -0.06
    _vs
    -0.06
     películ
    -0.06
    POSITIVE LOGITS
     Mut
    0.06
     асп
    0.06
     transports
    0.06
     výbě
    0.06
     conservatism
    0.06
     směrem
    0.06
     evacuation
    0.06
     inverted
    0.06
    _SHIFT
    0.06
     Aquarium
    0.05
    Act Density 0.280%

    No Known Activations