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

    Neuronpedia

    INDEX
    Explanations

    front

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     نیز
    -0.07
    adapt
    -0.06
    �
    -0.06
     Guru
    -0.06
    pletion
    -0.06
    Nearly
    -0.06
    丰
    -0.06
    络
    -0.06
    .text
    -0.06
    .green
    -0.06
    POSITIVE LOGITS
    (Method
    0.06
    _DOT
    0.06
    USIC
    0.06
    持
    0.06
    .cos
    0.06
    ..."↵
    0.06
     защит
    0.06
    ativos
    0.06
    (initial
    0.06
     deleteUser
    0.06
    Act Density 0.015%

    No Known Activations