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

    Neuronpedia

    INDEX
    Explanations

    New Deal programs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘴
    2.37
    𝘯
    2.34
    us
    2.14
    𝐃
    2.09
    fors
    2.05
    و
    2.03
    étique
    2.00
    textit
    1.99
     estradiol
    1.94
     MediaQuery
    1.93
    POSITIVE LOGITS
    kec
    2.03
     объ
    1.98
    نك
    1.91
     ===========
    1.90
    ಗೊಳ
    1.89
     bawah
    1.86
    ствовал
    1.85
    Corollary
    1.83
     akong
    1.81
     términos
    1.79
    Act Density 0.006%

    No Known Activations