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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    â
    -0.12
     â
    -0.10
     Î
    -0.10
    Â
    -0.09
    Î
    -0.09
    ١
    -0.09
    �
    -0.09
    'otu
    -0.09
     Ï
    -0.08
    -atụ
    -0.08
    POSITIVE LOGITS
    иф
    0.08
    циа
    0.08
     if
    0.08
    ↵
↵
↵
↵
↵
    0.08
     daca
    0.07
     alguna
    0.07
     *
↵
    0.07
    	if
    0.07
    аем
    0.07
     akin
    0.07
    Act Density 0.244%

    No Known Activations