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

    Neuronpedia

    INDEX
    Explanations

    matrix and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ąc
    0.42
    ajući
    0.40
    liery
    0.39
    opportunity
    0.39
    engelsk
    0.38
    endez
    0.38
    णाचा
    0.38
    angel
    0.38
     collaborations
    0.38
    avacan
    0.38
    POSITIVE LOGITS
     Tch
    0.42
     Tsche
    0.42
     ചെയ്
    0.41
     hombres
    0.41
     meninas
    0.41
     Gond
    0.40
     Pol
    0.39
     chicas
    0.38
     Riddle
    0.38
     зда
    0.38
    Act Density 0.002%

    No Known Activations