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

    Neuronpedia

    INDEX
    Explanations

    setbacks, coverage, or string properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     herramient
    0.44
     njegove
    0.43
    㗽
    0.42
    एनएस
    0.42
    Maya
    0.41
    更高的
    0.41
     interacción
    0.40
     技術
    0.40
     Servi
    0.39
     તેના
    0.39
    POSITIVE LOGITS
     run
    0.45
    bend
    0.43
    run
    0.43
     Run
    0.42
     Line
    0.41
    ло
    0.40
     Breaking
    0.40
    sept
    0.40
        
    0.40
     Compound
    0.40
    Act Density 0.011%

    No Known Activations