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

    Neuronpedia

    INDEX
    Explanations

    sulfur atoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    봐
    1.75
     ευρώ
    1.74
    يح
    1.73
    رض
    1.73
    τές
    1.73
    ران
    1.69
     domínio
    1.69
    nél
    1.68
    ह
    1.68
    ोरी
    1.64
    POSITIVE LOGITS
     xuyên
    2.02
    т
    1.96
    ות
    1.90
    ef
    1.86
    ate
    1.73
    alities
    1.72
    いろんな
    1.70
    ր
    1.67
    ality
    1.66
     छोड़कर
    1.63
    Act Density 0.001%

    No Known Activations