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

    Neuronpedia

    INDEX
    Explanations

    FROM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Helpers
    -0.07
     disputed
    -0.07
    _prepare
    -0.07
    Inverse
    -0.07
    opes
    -0.07
    Interop
    -0.07
    decode
    -0.07
    -play
    -0.06
    singleton
    -0.06
     했다
    -0.06
    POSITIVE LOGITS
     dokument
    0.06
    	range
    0.06
     mụn
    0.06
    HING
    0.06
    png
    0.06
    .toFloat
    0.06
     рань
    0.06
     disposit
    0.06
    準
    0.06
    ppelin
    0.06
    Act Density 0.007%

    No Known Activations