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

    Neuronpedia

    INDEX
    Explanations

    years followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ាល
    0.42
    ވަ
    0.39
    ﻭ
    0.39
    نت
    0.38
     annen
    0.37
    ματο
    0.37
    ود
    0.37
    手間
    0.36
     ovipares
    0.36
     entour
    0.36
    POSITIVE LOGITS
    chin
    0.50
    ī
    0.45
    ibb
    0.43
    onga
    0.41
    enda
    0.40
    ik
    0.40
    liga
    0.40
    imli
    0.39
    ád
    0.38
    ligt
    0.38
    Act Density 0.041%

    No Known Activations