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

    Neuronpedia

    INDEX
    Explanations

    Health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assertion
    -0.07
    .Context
    -0.06
     botanical
    -0.06
     Punjab
    -0.06
     Remarks
    -0.06
    TimeStamp
    -0.06
     internally
    -0.06
    .NORMAL
    -0.06
    Def
    -0.06
     ade
    -0.06
    POSITIVE LOGITS
    following
    0.07
    refund
    0.07
    _configs
    0.06
    ैं।
    0.06
    -three
    0.06
    vou
    0.06
     tecr
    0.06
    لات
    0.06
    ..↵↵↵↵
    0.06
     "**
    0.06
    Act Density 0.054%

    No Known Activations