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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clas
    -0.07
     nargs
    -0.07
     DST
    -0.06
     fungal
    -0.06
    ัค
    -0.06
    -0.06
    -0.06
    _pas
    -0.06
    inda
    -0.06
     다음
    -0.06
    POSITIVE LOGITS
    _CONDITION
    0.06
     lebih
    0.06
    覺
    0.06
     شكل
    0.06
    build
    0.06
    .analysis
    0.06
    .setHeader
    0.06
    oundation
    0.06
    防
    0.06
     của
    0.06
    Act Density 0.008%

    No Known Activations