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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ี
    0.56
     あり
    0.55
     жизнен
    0.55
     at
    0.54
     प्राचार्य
    0.48
    的人生
    0.47
    لیل
    0.46
    icrosoft
    0.46
    ย์
    0.46
    ியா
    0.46
    POSITIVE LOGITS
    acken
    0.46
    unki
    0.46
     raining
    0.42
     mustn
    0.42
     völl
    0.42
     Evidently
    0.41
    엠
    0.41
     centimetres
    0.40
     procede
    0.40
     Markers
    0.40
    Act Density 0.000%

    No Known Activations