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

    Neuronpedia

    INDEX
    Explanations

    px solid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंत्री
    0.39
     বিত
    0.39
    DBOutput
    0.38
    捃
    0.38
    قلال
    0.35
    ukkig
    0.34
     الرحيم
    0.33
    refreshToken
    0.33
     ପ
    0.33
    በባ
    0.33
    POSITIVE LOGITS
     solid
    4.69
    Solid
    4.53
     Solid
    4.47
    solid
    4.34
     SOLID
    3.81
    SOLID
    3.61
     solids
    3.52
     solide
    3.45
     sólido
    3.33
    固体
    3.33
    Act Density 0.064%

    No Known Activations