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

    Neuronpedia

    INDEX
    Explanations

    safety regulations and financial assets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    精确
    0.42
    可以直接
    0.41
    精华
    0.41
    Fetching
    0.40
     abbey
    0.39
     demonstrated
    0.39
     stimulated
    0.39
    贡献
    0.39
    Reuse
    0.39
    Ħ
    0.39
    POSITIVE LOGITS
    的想法
    0.50
    謗
    0.49
     defesa
    0.48
     commandments
    0.47
     dépos
    0.47
    の為
    0.47
     Partizan
    0.47
     Modelle
    0.46
     melawan
    0.46
    னமாக
    0.45
    Act Density 0.002%

    No Known Activations