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

    Neuronpedia

    INDEX
    Explanations

    SSL connection bypass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Substituting
    0.53
     Proses
    0.47
    댄
    0.46
     Especial
    0.45
     יד
    0.45
     rearrangement
    0.44
    ᒡ
    0.44
     процесса
    0.44
    を行い
    0.43
     Achievement
    0.43
    POSITIVE LOGITS
    的技术
    0.43
    meme
    0.42
     Hartford
    0.41
    的東西
    0.40
    peek
    0.40
    voren
    0.40
    sees
    0.39
    lied
    0.39
    listen
    0.38
    स्तू
    0.38
    Act Density 0.000%

    No Known Activations