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

    Neuronpedia

    INDEX
    Explanations

    neovim trigger config

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    로
    0.68
    ನ
    0.63
    ን
    0.63
    あ
    0.61
    İN
    0.60
    น
    0.60
    در
    0.59
    ع
    0.58
    Ε
    0.57
     diocese
    0.57
    POSITIVE LOGITS
    araja
    0.69
    ra
    0.65
    uk
    0.62
     koul
    0.60
    ol
    0.59
    ли
    0.59
    ches
    0.59
    lighter
    0.57
    arh
    0.57
    an
    0.57
    Act Density 0.003%

    No Known Activations