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

    Neuronpedia

    INDEX
    Explanations

    listen on port

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    0.61
     damn
    0.52
     damned
    0.48
     mover
    0.47
     ndani
    0.46
    ʟ
    0.46
    лость
    0.46
     tört
    0.45
    জি
    0.45
    oribus
    0.44
    POSITIVE LOGITS
     sexes
    0.49
     вот
    0.47
    বিহার
    0.46
     змо
    0.45
    invocation
    0.44
     exemple
    0.44
    sebastian
    0.43
    सूचना
    0.43
     ONU
    0.43
    टॉप
    0.43
    Act Density 0.009%

    No Known Activations