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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corn
    0.76
     petals
    0.73
     Corn
    0.71
     ಮುಖ್ಯ
    0.68
     carrots
    0.68
    jar
    0.68
     عل
    0.67
     продов
    0.66
    Wis
    0.65
     ከፍተኛ
    0.65
    POSITIVE LOGITS
     ref
    1.19
    ref
    1.05
     Ref
    1.03
    Ref
    0.98
     added
    0.87
    Added
    0.86
    REF
    0.86
     types
    0.86
     Added
    0.85
     typing
    0.85
    Act Density 0.306%

    No Known Activations