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

    Neuronpedia

    INDEX
    Explanations

    warnings and disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    セミナー
    0.47
    observable
    0.46
    Global
    0.46
    export
    0.46
    Lecture
    0.46
     TEXT
    0.45
     Sekunden
    0.45
    module
    0.45
    outcome
    0.45
    ================
    0.44
    POSITIVE LOGITS
     county
    0.54
     counties
    0.52
     Rhode
    0.50
    ربعة
    0.47
     underdog
    0.46
     jurisdic
    0.43
     दर्जन
    0.42
     freelance
    0.41
     Chrysler
    0.41
     oraș
    0.41
    Act Density 0.011%

    No Known Activations