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

    Neuronpedia

    INDEX
    Explanations

    sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    696
    -0.07
    tom
    -0.06
    week
    -0.06
    รถ
    -0.06
     아이
    -0.06
    Resp
    -0.06
     Sabbath
    -0.06
    (old
    -0.06
    há
    -0.06
    _prov
    -0.06
    POSITIVE LOGITS
     sources
    0.12
     Sources
    0.10
     source
    0.10
     sourced
    0.08
     visit
    0.07
    ources
    0.07
    EMAIL
    0.06
     alerted
    0.06
     clearing
    0.06
    .nt
    0.06
    Act Density 0.038%

    No Known Activations