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

    Neuronpedia

    INDEX
    Explanations

    talking about you and room

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     H
    0.41
     Russia
    0.41
    gunakan
    0.41
    aufnahme
    0.41
     USSR
    0.41
    ห
    0.40
    iend
    0.40
     Jealous
    0.39
     University
    0.39
     Y
    0.38
    POSITIVE LOGITS
     বোল
    0.46
     signifies
    0.46
     innebär
    0.45
     thermal
    0.45
     fxe
    0.44
     thermometers
    0.44
     decarbon
    0.44
     methanol
    0.44
    сү
    0.44
     froth
    0.44
    Act Density 0.010%

    No Known Activations