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
    TAB
    -0.06
     Write
    -0.06
    ush
    -0.06
     commanding
    -0.06
    STR
    -0.06
    状態
    -0.06
    _ticks
    -0.06
    	step
    -0.06
     mariage
    -0.06
     AGAIN
    -0.06
    POSITIVE LOGITS
     elkaar
    0.06
    ㅋㅋ
    0.06
     Andrea
    0.06
    _struct
    0.06
    .XtraBars
    0.06
     surprisingly
    0.06
    نى
    0.05
     ancient
    0.05
    ENDIF
    0.05
     Recursive
    0.05
    Act Density 0.037%

    No Known Activations