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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Rel
    -0.07
     caves
    -0.06
     environmental
    -0.06
    VERN
    -0.06
    _MY
    -0.06
    service
    -0.06
    Boot
    -0.06
    tolower
    -0.06
     Their
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     cyclist
    0.07
    вана
    0.07
    摄
    0.06
    失
    0.06
     Rabbi
    0.06
     напря
    0.06
     hiking
    0.06
    (actual
    0.06
    苦
    0.06
     apare
    0.06
    Act Density 0.038%

    No Known Activations