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

    Neuronpedia

    INDEX
    Explanations

    Theorem and definition statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ihanna
    0.53
     Rihanna
    0.49
     merasakan
    0.45
     tonnage
    0.44
    blackberry
    0.44
    distanceArray
    0.44
     Chinatown
    0.44
     migraines
    0.44
    काळी
    0.44
     hilly
    0.43
    POSITIVE LOGITS
    Theorem
    0.68
     theorem
    0.67
     theorems
    0.64
     Theorems
    0.60
     Lemma
    0.55
     Theorem
    0.55
    THEOREM
    0.54
     Definition
    0.54
    定理
    0.54
    Definition
    0.53
    Act Density 0.011%

    No Known Activations