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

    Neuronpedia

    INDEX
    Explanations

    equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     birey
    -0.07
    <strong
    -0.07
    FlowLayout
    -0.06
     cub
    -0.06
     preparations
    -0.06
    (!(
    -0.06
    (cmp
    -0.06
     ubuntu
    -0.06
    depart
    -0.06
    .valor
    -0.06
    POSITIVE LOGITS
     股
    0.07
    ufact
    0.07
    coin
    0.07
     account
    0.07
    abling
    0.07
    asic
    0.06
    形成
    0.06
    ти
    0.06
    lescope
    0.06
     insufficient
    0.06
    Act Density 0.005%

    No Known Activations