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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jection
    -0.07
     range
    -0.06
    .ButterKnife
    -0.06
    dealloc
    -0.06
    self
    -0.06
     Mature
    -0.06
    publisher
    -0.06
     metodo
    -0.06
    سازی
    -0.06
     wiped
    -0.06
    POSITIVE LOGITS
     gql
    0.07
    重
    0.07
     sayf
    0.07
    .ep
    0.07
    _VALID
    0.07
    Rows
    0.06
    农业
    0.06
     Firewall
    0.06
    atar
    0.06
    StateChanged
    0.06
    Act Density 0.014%

    No Known Activations