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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    диви
    -0.08
     Perfect
    -0.07
     caught
    -0.07
    enton
    -0.07
     ett
    -0.07
     homicides
    -0.06
     Please
    -0.06
     esi
    -0.06
    acos
    -0.06
    (det
    -0.06
    POSITIVE LOGITS
    ısız
    0.07
    IPH
    0.06
     cou
    0.06
    %%↵
    0.06
    щее
    0.06
     České
    0.06
    спіль
    0.06
    
    0.06
    _ASS
    0.06
     Πρω
    0.06
    Act Density 0.019%

    No Known Activations