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

    Neuronpedia

    INDEX
    Explanations

    Dynamic Typing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的角度
    0.40
     rhizosphere
    0.39
    ರೆಯ
    0.37
     Kamera
    0.36
     অবস্থানে
    0.36
    㳖
    0.36
     ক্যামেরা
    0.36
     زاويه
    0.35
    痫
    0.35
    FAKE
    0.35
    POSITIVE LOGITS
     rate
    0.38
     something
    0.36
    |
    0.36
     better
    0.34
     דבר
    0.33
    ete
    0.33
     вз
    0.33
     corr
    0.33
     conduct
    0.32
    ↵
    0.32
    Act Density 0.000%

    No Known Activations