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

    Neuronpedia

    INDEX
    Explanations

    evidence and quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yrıca
    0.54
     능
    0.46
    ası
    0.44
    我也
    0.43
     όλα
    0.43
    ác
    0.42
    ılar
    0.42
    ąd
    0.41
    ılık
    0.41
    áp
    0.41
    POSITIVE LOGITS
    නම්
    0.50
     sandwiched
    0.47
    aadhar
    0.47
     conspicuously
    0.47
    Bollywood
    0.46
     unsus
    0.45
    batch
    0.45
     Sanjay
    0.45
     condemning
    0.45
     comprising
    0.44
    Act Density 0.002%

    No Known Activations