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

    Neuronpedia

    INDEX
    Explanations

    the shortest option identified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    0.54
    ：
    0.51
    in
    0.50
    <0xC2>
    0.46
     –
    0.45
     new
    0.44
     in
    0.44
     ag
    0.44
     first
    0.44
     instantly
    0.41
    POSITIVE LOGITS
     thrombocyt
    0.59
    0.55
    ㄼ
    0.54
     Lessor
    0.53
    Plaintiff
    0.52
     birefring
    0.52
    أي
    0.52
     EtOH
    0.51
    Nicht
    0.51
     gdf
    0.51
    Act Density 0.000%

    No Known Activations