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

    Neuronpedia

    INDEX
    Explanations

    fanfic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    9
    0.74
    5
    0.70
    t
    0.69
    nesia
    0.69
    los
    0.67
    lions
    0.64
    frequencies
    0.64
    ﻠ
    0.64
    ﺪ
    0.64
    sonic
    0.63
    POSITIVE LOGITS
    น
    0.71
     attribu
    0.65
    </a>
    0.65
     executes
    0.65
     書い
    0.63
     konkuren
    0.63
     aggior
    0.62
     ἔ
    0.62
     appre
    0.62
     รวม
    0.62
    Act Density 0.001%

    No Known Activations