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

    Neuronpedia

    INDEX
    Explanations

    Searching and filtering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ют
    -0.07
    ография
    -0.06
    rical
    -0.06
    сов
    -0.06
    lán
    -0.06
    ints
    -0.06
    composite
    -0.06
     Parr
    -0.06
    ậu
    -0.06
    Pa
    -0.06
    POSITIVE LOGITS
    彼女
    0.07
     δι
    0.07
    _checkpoint
    0.06
     статус
    0.06
    ENSION
    0.06
     Rhino
    0.06
     hoses
    0.06
     бар
    0.06
     gouver
    0.06
    ีโอ
    0.06
    Act Density 0.022%

    No Known Activations