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

    Neuronpedia

    INDEX
    Explanations

    employer-sponsored group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Појединачна
    0.40
     Manik
    0.40
     Monetary
    0.38
     ADB
    0.37
     Celebrity
    0.37
     Dame
    0.37
    idi
    0.36
    RunWith
    0.36
     Sundance
    0.36
    casting
    0.36
    POSITIVE LOGITS
     विस्फोट
    0.45
     explosions
    0.41
    Arc
    0.40
    Guide
    0.40
     বিস্ফো
    0.40
    Members
    0.39
    leden
    0.39
    னெ
    0.39
    诱
    0.38
    氳
    0.38
    Act Density 0.000%

    No Known Activations