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

    Neuronpedia

    INDEX
    Explanations

    Calculating time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    minute
    -0.07
    cnt
    -0.06
    iotic
    -0.06
    福利
    -0.06
     zeroes
    -0.06
    .compute
    -0.06
    °C
    -0.06
    (rate
    -0.06
     recruitment
    -0.06
    .house
    -0.06
    POSITIVE LOGITS
     Tk
    0.06
    CancelButton
    0.06
    (DE
    0.06
     потрібно
    0.06
    //↵↵↵
    0.06
     bomber
    0.06
    :params
    0.06
    /red
    0.06
     नई
    0.06
     Seth
    0.06
    Act Density 0.003%

    No Known Activations