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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зон
    -0.07
     Again
    -0.07
     Haz
    -0.07
     현재
    -0.07
    标语
    -0.07
    ])),↵
    -0.07
    助け
    -0.06
    LET
    -0.06
     factor
    -0.06
     Dread
    -0.06
    POSITIVE LOGITS
     edits
    0.07
    خصوص
    0.07
    keyboard
    0.07
    _GL
    0.07
    ⁉
    0.07
    _FULLSCREEN
    0.07
    pixels
    0.07
    柏林
    0.07
     الإرهاب
    0.07
    (asset
    0.07
    Act Density 0.002%

    No Known Activations