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

    Neuronpedia

    INDEX
    Explanations

    International abbreviations/acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鹿
    -0.07
     spiritual
    -0.07
    _DEFINITION
    -0.06
     Haram
    -0.06
    “So
    -0.06
    ESA
    -0.06
    "So
    -0.06
    律宾
    -0.06
    _flux
    -0.06
    illian
    -0.06
    POSITIVE LOGITS
    PreparedStatement
    0.07
    \Routing
    0.06
     peny
    0.06
    лож
    0.06
    UTION
    0.06
     shutting
    0.06
    Norm
    0.06
     Prev
    0.06
    charging
    0.06
    captures
    0.06
    Act Density 0.162%

    No Known Activations