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

    Neuronpedia

    INDEX
    Explanations

    Alfred followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    2.53
    ح
    2.48
    が増
    2.42
    ا
    2.25
    ط
    2.16
    ت
    2.09
    侗
    2.09
    が一
    2.08
    很多的
    2.05
    u
    2.05
    POSITIVE LOGITS
    ate
    2.25
    '
    2.09
    \"
    2.05
    ’
    1.98
    um
    1.87
    ation
    1.85
    ant
    1.84
    iv
    1.83
    ά
    1.81
     ailing
    1.77
    Act Density 0.001%

    No Known Activations