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

    Neuronpedia

    INDEX
    Explanations

    Data files/formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dung
    -0.06
     ----------------------------------------------------------------------------↵
    -0.06
    �
    -0.06
    .NonNull
    -0.06
     Bernard
    -0.06
     прек
    -0.06
    анні
    -0.06
    llvm
    -0.06
    .fasterxml
    -0.06
    <UnityEngine
    -0.06
    POSITIVE LOGITS
     tricks
    0.07
    _Integer
    0.07
    мос
    0.07
    [min
    0.06
     Wallet
    0.06
    těž
    0.06
    BUS
    0.06
    _RECE
    0.06
    ruk
    0.06
    _PED
    0.06
    Act Density 0.103%

    No Known Activations