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

    Neuronpedia

    INDEX
    Explanations

    logic gates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    獐
    0.49
     бухгал
    0.42
     ένας
    0.42
     давно
    0.41
     ঘটনা
    0.40
     ماس
    0.39
    া
    0.39
     dug
    0.39
    绅
    0.39
     нужны
    0.39
    POSITIVE LOGITS
    트
    0.47
    ikke
    0.47
     fpr
    0.47
     recover
    0.46
     Cori
    0.44
    }?
    0.44
    ocytes
    0.43
    níka
    0.43
     exercice
    0.43
     her
    0.42
    Act Density 0.000%

    No Known Activations