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

    Neuronpedia

    INDEX
    Explanations

    control and over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    0.71
    linking
    0.70
    icillin
    0.70
     Speaking
    0.69
    諦
    0.66
     foreground
    0.66
    await
    0.65
     completing
    0.65
    rekking
    0.65
    Speaking
    0.65
    POSITIVE LOGITS
    Over
    1.15
     over
    1.10
     Over
    1.09
     над
    1.01
     OVER
    0.98
     över
    0.95
    over
    0.94
     semej
    0.91
    OVER
    0.89
    omegranate
    0.88
    Act Density 0.316%

    No Known Activations