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

    Neuronpedia

    INDEX
    Explanations

    PCR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zelf
    -0.07
     thu
    -0.07
    	dest
    -0.07
    「そう
    -0.07
     seri
    -0.07
    unlink
    -0.07
     проти
    -0.06
    	ep
    -0.06
    encrypted
    -0.06
     vite
    -0.06
    POSITIVE LOGITS
    ी↵
    0.06
     Feld
    0.06
    ROLS
    0.06
    са
    0.06
     survived
    0.06
     Otto
    0.06
    ニー
    0.05
    _tolerance
    0.05
    ísticas
    0.05
    먹
    0.05
    Act Density 0.061%

    No Known Activations