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

    Neuronpedia

    INDEX
    Explanations

    contexts where time or conditions are discussed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    個
    0.49
    individ
    0.49
     کاربران
    0.49
    зара
    0.42
     برخی
    0.42
     individ
    0.42
     denomin
    0.42
     individualism
    0.41
    individu
    0.41
     cambi
    0.41
    POSITIVE LOGITS
     ৬
    0.44
     expiry
    0.42
    ᱼ
    0.41
     mãi
    0.40
     năm
    0.40
    measuredangle
    0.40
    netHex
    0.40
     accompanies
    0.40
     suốt
    0.39
    MainActivityTest
    0.39
    Act Density 0.007%

    No Known Activations