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

    Neuronpedia

    INDEX
    Explanations

    next timeframes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulations
    0.42
    sets
    0.41
     готов
    0.41
    ULATIONS
    0.40
    planes
    0.40
    ulet
    0.40
     simplification
    0.39
    CLUDES
    0.39
     आहेत
    0.39
     prin
    0.38
    POSITIVE LOGITS
     pengalaman
    0.51
    观看
    0.49
     était
    0.48
    颦
    0.48
     저
    0.48
     Tonight
    0.46
     tatsächlich
    0.46
    Watching
    0.45
     tonight
    0.45
     تجربه
    0.43
    Act Density 0.001%

    No Known Activations