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

    Neuronpedia

    INDEX
    Explanations

    movements or state changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.57
    ’
    0.57
    '
    0.50
     myself
    0.48
     was
    0.48
    of
    0.47
     Mule
    0.46
     अपनी
    0.44
     свои
    0.43
    0.42
    POSITIVE LOGITS
    ላቸው
    0.64
    ，
    0.55
    ，$
    0.50
    Ми
    0.48
    ،
    0.47
    ，《
    0.46
     demais
    0.46
     언제
    0.46
    สำหรับการ
    0.45
    ीत
    0.45
    Act Density 0.135%

    No Known Activations