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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     平方
    -0.07
     ژاپ
    -0.07
    /client
    -0.07
     Gay
    -0.07
    teborg
    -0.06
    opro
    -0.06
    ा↵↵
    -0.06
     onItemClick
    -0.06
    osa
    -0.06
     interdisciplinary
    -0.06
    POSITIVE LOGITS
     góc
    0.06
    abilité
    0.06
     Nah
    0.06
    ROSS
    0.06
    κρα
    0.06
     pand
    0.06
     PROF
    0.06
    exels
    0.06
     leased
    0.05
    =re
    0.05
    Act Density 0.024%

    No Known Activations