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

    Neuronpedia

    INDEX
    Explanations

    numbers and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لینک
    0.43
    रों
    0.40
     bitOp
    0.39
     convertido
    0.38
    旕
    0.38
     בעי
    0.37
    箐
    0.37
     convierten
    0.37
     үч
    0.36
     competição
    0.36
    POSITIVE LOGITS
     vs
    0.56
     minus
    0.56
     versus
    0.55
     -
    0.54
     −
    0.51
     —
    0.50
     Minus
    0.50
     $-
    0.50
    _{+}-
    0.49
     compared
    0.45
    Act Density 0.022%

    No Known Activations