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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    說
    -0.07
    _swap
    -0.07
    elt
    -0.07
     režim
    -0.06
    Profit
    -0.06
    lad
    -0.06
     language
    -0.06
     привод
    -0.06
     grain
    -0.06
     lot
    -0.06
    POSITIVE LOGITS
     Cir
    0.07
    onto
    0.07
     asi
    0.06
     Frem
    0.06
    General
    0.06
    oklyn
    0.06
     Martins
    0.06
    ITHER
    0.06
    铁路
    0.06
    among
    0.06
    Act Density 0.015%

    No Known Activations