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

    Neuronpedia

    INDEX
    Explanations

    location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ها
    1.78
    般的
    1.76
    LER
    1.72
     trialComponents
    1.69
    Ciao
    1.68
    เป็น
    1.62
    ເປັນ
    1.59
     absorbers
    1.56
    는
    1.55
    넬
    1.55
    POSITIVE LOGITS
    nın
    2.83
    nymi
    2.52
    deki
    2.47
    larda
    2.45
    ى
    2.42
    iation
    2.39
    ない
    2.36
    pecific
    2.31
    ce
    2.27
    ned
    2.27
    Act Density 0.063%

    No Known Activations