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

    Neuronpedia

    INDEX
    Explanations

    domain name or safe food

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ikia
    0.57
    atoi
    0.52
    bild
    0.52
    ua
    0.51
    ombra
    0.50
    ickej
    0.46
    ਸ਼ਨ
    0.46
    rende
    0.46
    riwal
    0.46
     समानार्थी
    0.46
    POSITIVE LOGITS
    ্রো
    0.52
    嵃
    0.52
    ו
    0.50
    沚
    0.49
     così
    0.48
     outputs
    0.47
    通过
    0.47
     hiện
    0.46
     trực
    0.46
     רו
    0.45
    Act Density 0.000%

    No Known Activations