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

    Neuronpedia

    INDEX
    Explanations

    demons influencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grandeur
    0.48
    CH
    0.47
     gutted
    0.45
     vectors
    0.44
     مكت
    0.44
     desec
    0.44
    ocs
    0.43
    ersonic
    0.43
     deple
    0.43
     lắng
    0.42
    POSITIVE LOGITS
    jogador
    0.58
    categorias
    0.49
    lige
    0.49
     personagens
    0.48
     influencia
    0.47
    ⴳ
    0.47
    ewöhn
    0.45
    define
    0.44
    been
    0.44
    lée
    0.43
    Act Density 0.000%

    No Known Activations