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

    Neuronpedia

    INDEX
    Explanations

    levels of or relateds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    強制
    0.47
    胸
    0.46
     hated
    0.46
    感染
    0.43
    サイズの
    0.42
    雄
    0.42
    Жен
    0.42
    大手
    0.41
    强制
    0.41
     महिलाओं
    0.41
    POSITIVE LOGITS
     konfigur
    0.45
     angles
    0.44
     kapp
    0.42
     enables
    0.42
    nál
    0.42
     simult
    0.42
    ామ
    0.42
    ax
    0.41
     configurations
    0.41
     ава
    0.41
    Act Density 0.001%

    No Known Activations