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

    Neuronpedia

    INDEX
    Explanations

    such AI abilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்தின்
    0.35
    *,
    0.35
     inextricably
    0.34
    ,​
    0.34
     أثناء
    0.33
    ile
    0.32
     細胞
    0.32
     уйнарга
    0.32
     waitUntil
    0.31
    )$,
    0.31
    POSITIVE LOGITS
     solche
    0.49
     이런
    0.48
     tantos
    0.48
     slike
    0.46
     ilyen
    0.46
     nicer
    0.45
    这么
    0.44
     tantas
    0.44
     этих
    0.42
     sowas
    0.42
    Act Density 0.001%

    No Known Activations