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

    Neuronpedia

    INDEX
    Explanations

    reasoning or justification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ээ
    0.47
     muziek
    0.44
     newMovie
    0.42
     jaane
    0.42
     seconda
    0.41
     music
    0.41
    тература
    0.40
    widet
    0.39
     nuove
    0.39
     laughs
    0.39
    POSITIVE LOGITS
     कर्
    0.41
     muốn
    0.40
     Similarly
    0.40
     dispositivo
    0.39
     нуле
    0.39
     Zero
    0.38
     जीरो
    0.38
     zero
    0.37
    bate
    0.37
     didn
    0.37
    Act Density 0.000%

    No Known Activations