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

    Neuronpedia

    INDEX
    Explanations

    ,”

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.87
    (
    0.78
     மற்றும்
    0.77
     /
    0.73
    :
    0.73
    和
    0.73
     or
    0.73
     :
    0.73
    /
    0.71
     и
    0.70
    POSITIVE LOGITS
    他說
    1.00
    他说
    0.91
     قال
    0.90
     rekao
    0.89
     తెలిపారు
    0.88
    said
    0.86
     sagte
    0.86
    says
    0.86
     Says
    0.86
     manifestó
    0.86
    Act Density 0.005%

    No Known Activations