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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Entries
    -0.07
    .getProject
    -0.06
    minated
    -0.06
    cribed
    -0.06
     desn
    -0.06
    .Cross
    -0.06
     sol
    -0.06
     Collision
    -0.05
    ({})↵
    -0.05
     Поч
    -0.05
    POSITIVE LOGITS
     AVR
    0.09
     кур
    0.07
    _NB
    0.07
    ワイト
    0.07
     datePicker
    0.07
    .listBox
    0.07
    ctrine
    0.07
    agara
    0.07
    (火
    0.07
     проек
    0.07
    Act Density 0.000%

    No Known Activations