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

    Neuronpedia

    INDEX
    Explanations

    PID and classifying terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     driver
    0.50
    لى
    0.49
     sunny
    0.48
     potable
    0.47
    дна
    0.46
     conserve
    0.46
     patio
    0.46
     nearby
    0.45
    G
    0.45
     docking
    0.45
    POSITIVE LOGITS
    ası
    0.54
    issons
    0.54
    䉿
    0.54
    acchus
    0.52
    dür
    0.51
    borg
    0.49
    komm
    0.49
    oja
    0.48
    adig
    0.47
    ările
    0.47
    Act Density 0.000%

    No Known Activations