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

    Neuronpedia

    INDEX
    Explanations

    numerals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eware
    -0.07
    All
    -0.06
    posure
    -0.06
    .period
    -0.06
    byter
    -0.06
    lake
    -0.06
    andard
    -0.06
    _profiles
    -0.06
    .ad
    -0.06
    ARB
    -0.06
    POSITIVE LOGITS
     조선
    0.07
     francouz
    0.07
    Sets
    0.06
     초기
    0.06
     Settings
    0.06
    laması
    0.06
    ()?
    0.06
     cpf
    0.06
    Yaw
    0.06
    inesis
    0.06
    Act Density 0.023%

    No Known Activations