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

    Neuronpedia

    INDEX
    Explanations

    programming loop variables and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.05
    an
    0.99
    textbf
    0.86
    ../
    0.83
    os
    0.77
    oretically
    0.76
    a
    0.76
    *_
    0.75
    {
    0.73
    ../../
    0.72
    POSITIVE LOGITS
    寺
    0.99
     percentage
    0.91
     percentuale
    0.91
    ణు
    0.87
     outfit
    0.85
    ἂ
    0.84
     rass
    0.84
    ก็จะ
    0.84
     Ча
    0.82
    াদিগকে
    0.81
    Act Density 0.282%

    No Known Activations