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

    Neuronpedia

    INDEX
    Explanations

    full file path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     interstices
    0.45
    effici
    0.41
     metastability
    0.40
    Concini
    0.40
    orifice
    0.39
    之地
    0.39
    Differential
    0.39
     psychosis
    0.39
     ইহ
    0.38
     orifice
    0.38
    POSITIVE LOGITS
     bread
    0.45
     Brewery
    0.44
     Google
    0.44
     Bread
    0.43
     vict
    0.42
     Share
    0.42
     Premier
    0.41
     culture
    0.41
     google
    0.40
     current
    0.40
    Act Density 0.010%

    No Known Activations