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

    Neuronpedia

    INDEX
    Explanations

    ensures compatibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ïde
    0.42
    idegg
    0.42
    osed
    0.41
    ųjų
    0.40
    ulfite
    0.39
    izando
    0.38
     Kepala
    0.38
    ních
    0.38
    izador
    0.38
    ineros
    0.38
    POSITIVE LOGITS
     arrive
    0.44
     loading
    0.42
    وصل
    0.40
     enjoy
    0.39
    มาร
    0.39
     arrived
    0.39
     Burg
    0.38
     larceny
    0.38
     durations
    0.38
    contin
    0.38
    Act Density 0.000%

    No Known Activations