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

    Neuronpedia

    INDEX
    Explanations

    tension and strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     характеризу
    0.59
     dessert
    0.58
     delicioso
    0.57
     hybrid
    0.56
     possède
    0.56
     er
    0.55
     aspirin
    0.55
     codec
    0.55
    மான்
    0.54
     t
    0.54
    POSITIVE LOGITS
    such
    0.61
    UTC
    0.59
    ات
    0.55
    slightly
    0.54
    Adjust
    0.54
    Cau
    0.54
    ्ता
    0.54
    Au
    0.53
    Huff
    0.53
     .(
    0.52
    Act Density 0.002%

    No Known Activations