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

    Neuronpedia

    INDEX
    Explanations

    depressed state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getroffen
    0.45
    сий
    0.42
    माटर
    0.42
     വളരെ
    0.42
    有望
    0.41
    迅速
    0.41
    簡単
    0.40
    采样
    0.40
    мент
    0.40
    ラーメン
    0.40
    POSITIVE LOGITS
     vols
    0.47
    coles
    0.46
    doo
    0.46
     Mint
    0.45
    findBy
    0.45
    bs
    0.45
    iii
    0.44
    yo
    0.44
    in
    0.44
    rows
    0.43
    Act Density 11.721%

    No Known Activations