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

    Neuronpedia

    INDEX
    Explanations

    partial modification or derivative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kelamin
    1.41
    ين
    1.29
    很多
    1.23
    нили
    1.18
    ند
    1.16
    గే
    1.16
    et
    1.13
    )>=
    1.12
     ganhou
    1.11
    ન
    1.11
    POSITIVE LOGITS
    ہ
    1.58
    り
    1.30
     furtherance
    1.20
     inch
    1.19
    eel
    1.19
     oscillation
    1.16
    你
    1.14
     irrigation
    1.13
    iled
    1.09
    eled
    1.09
    Act Density 0.028%

    No Known Activations