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

    Neuronpedia

    INDEX
    Explanations

    WiFi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    372
    -0.07
    _XDECREF
    -0.06
     눈
    -0.06
    790
    -0.06
    GIN
    -0.06
     nutshell
    -0.06
    742
    -0.06
    970
    -0.06
    Rom
    -0.06
     연락
    -0.06
    POSITIVE LOGITS
    -б
    0.07
     pada
    0.06
     Explicit
    0.06
    enties
    0.06
    etermination
    0.06
    /entity
    0.06
     kred
    0.06
    overwrite
    0.06
    อาจ
    0.06
    riter
    0.06
    Act Density 0.014%

    No Known Activations