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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     almak
    -0.07
     кух
    -0.07
    586
    -0.06
    vo
    -0.06
     '');↵
    -0.06
    nesení
    -0.06
    řev
    -0.06
    587
    -0.06
    _fitness
    -0.06
    实
    -0.06
    POSITIVE LOGITS
     gastro
    0.07
     wb
    0.06
     reactor
    0.06
    .choose
    0.06
    Ing
    0.06
    errer
    0.06
     Establishment
    0.06
    peon
    0.06
    .nano
    0.06
    arith
    0.06
    Act Density 0.189%

    No Known Activations