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

    Neuronpedia

    INDEX
    Explanations

    domestic violence hotline and treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сля
    0.65
    椂
    0.63
    ลักษณ์
    0.61
    Buch
    0.61
     Segmentation
    0.59
     Guten
    0.58
     रिक्त
    0.58
    濋
    0.57
    जेक्ट
    0.57
     আদায়
    0.57
    POSITIVE LOGITS
     Mathis
    0.68
    baseHP
    0.58
    軒
    0.58
    ้อย
    0.55
    maxx
    0.53
    visa
    0.52
     Markham
    0.52
    aporan
    0.51
    illet
    0.51
     réfl
    0.51
    Act Density 0.037%

    No Known Activations