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

    Neuronpedia

    INDEX
    Explanations

    a \[word]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proactively
    0.43
     classifies
    0.41
     সঠিকভাবে
    0.39
     afield
    0.39
     предусматри
    0.39
     equates
    0.38
    idän
    0.37
     getAll
    0.37
    anneer
    0.37
    zyna
    0.36
    POSITIVE LOGITS
     photons
    0.44
     courage
    0.43
     agony
    0.41
     glistening
    0.41
     laughter
    0.41
     darkness
    0.41
     lumière
    0.40
     liberation
    0.40
     tyranny
    0.40
    ほどの
    0.39
    Act Density 0.190%

    No Known Activations