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

    Neuronpedia

    INDEX
    Explanations

    will not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あとは
    0.86
    くらい
    0.79
    倒是
    0.76
    的情况下
    0.75
     정도로
    0.73
    むしろ
    0.71
    われます
    0.67
    それで
    0.65
    ぐらい
    0.65
    ிலேயே
    0.61
    POSITIVE LOGITS
     not
    6.88
    not
    6.10
     Not
    5.78
    Not
    5.74
     NOT
    5.21
    NOT
    4.81
     όχι
    4.53
     nicht
    4.31
     ikke
    4.05
     niet
    3.90
    Act Density 1.562%

    No Known Activations