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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Test
    -0.07
     Later
    -0.07
    тар
    -0.06
     beri
    -0.06
    -cond
    -0.06
     Toilet
    -0.06
    �
    -0.06
     PU
    -0.06
    ZF
    -0.06
     power
    -0.06
    POSITIVE LOGITS
     ########.
    0.07
     tvoř
    0.07
     청
    0.06
     antique
    0.06
    ичні
    0.06
    PHPExcel
    0.06
     velik
    0.06
    -found
    0.06
     hotelu
    0.06
     şiddet
    0.06
    Act Density 0.022%

    No Known Activations