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

    Neuronpedia

    INDEX
    Explanations

    found or exists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ™.
    0.51
    attrs
    0.49
    yml
    0.48
    సర
    0.46
    値を
    0.45
     **
    0.45
     ним
    0.45
    तिम
    0.44
    ToLower
    0.44
    ศาสตร์
    0.44
    POSITIVE LOGITS
    에
    0.86
     wholly
    0.86
     keenly
    0.81
    ગાહી
    0.78
     utterly
    0.78
     extremely
    0.77
    Tidak
    0.77
     widely
    0.77
    𝚞
    0.76
    湇
    0.75
    Act Density 0.006%

    No Known Activations