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

    Neuronpedia

    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tracks
    -0.07
    PRETTY
    -0.06
     праців
    -0.06
    ,void
    -0.06
     discredit
    -0.06
    leftrightarrow
    -0.06
     по
    -0.06
     mouths
    -0.06
     Recru
    -0.06
    StringLength
    -0.06
    POSITIVE LOGITS
    /detail
    0.07
    Column
    0.06
     Parameter
    0.06
    	ZEPHIR
    0.06
    German
    0.06
     marvel
    0.06
     Tahoe
    0.06
    _win
    0.06
    .internal
    0.06
    圭
    0.06
    Act Density 0.000%

    No Known Activations