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

    Neuronpedia

    INDEX
    Explanations

    different or the same

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     част
    0.44
     función
    0.44
     CI
    0.43
    तरीय
    0.43
     linea
    0.42
     I
    0.42
     documento
    0.41
     decentral
    0.41
     Autonomous
    0.41
     airliner
    0.41
    POSITIVE LOGITS
    ت
    0.57
    ForRule
    0.49
    زب
    0.49
    패
    0.48
    سين
    0.48
    చ్చే
    0.47
    িন্দা
    0.46
    ermat
    0.45
    spro
    0.45
    та
    0.44
    Act Density 0.001%

    No Known Activations