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

    Neuronpedia

    INDEX
    Explanations

    semantic, standard, code, ground, super, train

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hypertrophy
    0.35
     explic
    0.33
    अप्र
    0.32
    ើន
    0.32
     auctor
    0.32
     theoret
    0.31
    citenamefont
    0.31
     longitudinale
    0.31
     ausgest
    0.31
    theoretic
    0.31
    POSITIVE LOGITS
     这是
    0.32
     Pancake
    0.31
     Wall
    0.31
     Summer
    0.31
     LED
    0.31
     Airbnb
    0.30
     లేదా
    0.30
     Woodlands
    0.30
     Flying
    0.30
     Led
    0.30
    Act Density 0.001%

    No Known Activations