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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _unref
    -0.07
    /thread
    -0.07
    ungeons
    -0.06
    把
    -0.06
    겠
    -0.06
    ecimal
    -0.06
     مذه
    -0.06
     باست
    -0.06
    	canvas
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    >x
    0.08
     listing
    0.07
     Istanbul
    0.07
    ilar
    0.06
    consistent
    0.06
     northeast
    0.06
     성
    0.06
    vidia
    0.06
     divider
    0.06
     Polynomial
    0.06
    Act Density 0.000%

    No Known Activations