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

    Neuronpedia

    INDEX
    Explanations

    URLs pointing to blog posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asil
    0.39
     Antio
    0.36
     Анти
    0.36
    蛸
    0.35
     SR
    0.35
    कालीन
    0.35
     সহিংস
    0.35
     Anti
    0.34
    qat
    0.34
     limes
    0.34
    POSITIVE LOGITS
    Boss
    0.40
    Dar
    0.36
    Village
    0.36
    Bah
    0.35
    Diary
    0.35
     boson
    0.34
    undering
    0.34
     Boss
    0.34
    Virus
    0.34
    Bet
    0.34
    Act Density 0.007%

    No Known Activations