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

    Neuronpedia

    INDEX
    Explanations

    transition to help or question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ফুল্ল
    1.44
    𝗶
    1.41
    り
    1.40
    𝑠
    1.38
    ي
    1.37
    𝑖
    1.35
    𝑛
    1.34
     guineas
    1.30
    悱
    1.29
    नव
    1.29
    POSITIVE LOGITS
    ے
    1.36
    ly
    1.25
    ูณ
    1.21
     держав
    1.16
    жи
    1.16
    odeon
    1.14
    gini
    1.12
    ্স
    1.10
     уж
    1.08
    he
    1.08
    Act Density 0.024%

    No Known Activations