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

    Neuronpedia

    INDEX
    Explanations

    best for specific audiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nmea
    0.35
    ieken
    0.33
    engono
    0.32
    components
    0.31
    dtype
    0.31
     dimethyl
    0.30
     enacted
    0.30
    plasia
    0.30
    getElementsBy
    0.29
     emitted
    0.29
    POSITIVE LOGITS
     beginners
    0.70
     beginner
    0.60
     Beginners
    0.57
     lovers
    0.57
     anyone
    0.55
    初心者
    0.55
     novice
    0.54
     aspiring
    0.52
    beginner
    0.52
     believers
    0.49
    Act Density 0.545%

    No Known Activations