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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hy
    -0.07
     delegate
    -0.07
     semantic
    -0.07
     Wa
    -0.07
     ga
    -0.06
     UD
    -0.06
     isEqual
    -0.06
    _markers
    -0.06
     تور
    -0.06
     назива
    -0.06
    POSITIVE LOGITS
    ält
    0.06
    inth
    0.06
     средств
    0.06
     getters
    0.06
    对
    0.06
    老
    0.06
    (found
    0.06
    .detail
    0.06
    >>↵
    0.06
    くだ
    0.06
    Act Density 0.000%

    No Known Activations