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

    Neuronpedia

    INDEX
    Explanations

    She Hulk struggling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diosa
    1.35
     удосто
    1.33
    adolid
    1.30
     entsprechend
    1.23
     붙
    1.23
     brah
    1.22
     stir
    1.22
    ৃত্বে
    1.22
     identifiers
    1.21
     eclipse
    1.21
    POSITIVE LOGITS
    y
    1.21
    ᴜ
    1.16
    min
    1.03
    breaker
    0.99
    moderate
    0.98
    ooo
    0.96
    oooo
    0.96
    house
    0.95
    fire
    0.94
    countdown
    0.94
    Act Density 0.019%

    No Known Activations