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

    Neuronpedia

    INDEX
    Explanations

    significance, signifier, significantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     수는
    0.47
    ళి
    0.43
    ใส่
    0.41
    নারায়ণ
    0.40
    ใส
    0.40
    糈
    0.39
     মৃতের
    0.38
    磷
    0.38
     Machinery
    0.38
     নদী
    0.37
    POSITIVE LOGITS
    ificance
    1.15
    ificantly
    1.13
    ificant
    1.01
    ifiant
    1.00
    ifiers
    0.93
    fic
    0.92
    ific
    0.88
    ificante
    0.88
    atures
    0.85
    ifier
    0.84
    Act Density 0.026%

    No Known Activations