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

    Neuronpedia

    INDEX
    Explanations

    specific examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بیشتری
    0.44
    嬤
    0.44
    PreferenceKey
    0.43
     센
    0.42
    ⅞
    0.42
     twentieth
    0.42
     व्याकरण
    0.42
     rational
    0.41
    醛
    0.41
    遊び
    0.40
    POSITIVE LOGITS
    L
    0.61
    <0x0D>
    0.55
    D
    0.53
    O
    0.51
    ované
    0.51
                            
    0.49
    Dash
    0.49
    N
    0.48
    荐
    0.48
    false
    0.48
    Act Density 0.002%

    No Known Activations