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

    Neuronpedia

    INDEX
    Explanations

    new physics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strtolower
    -0.06
    Sou
    -0.06
    MENTS
    -0.06
    =my
    -0.06
    _SHIFT
    -0.06
    (Dense
    -0.06
     Та
    -0.06
    SUB
    -0.06
     lament
    -0.06
    Perhaps
    -0.06
    POSITIVE LOGITS
     yaşında
    0.07
    peek
    0.06
     {"
    0.06
    cpf
    0.06
    uD
    0.06
     Alic
    0.06
    .variant
    0.06
     pref
    0.06
    .filePath
    0.06
     MethodInfo
    0.06
    Act Density 0.027%

    No Known Activations