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

    Neuronpedia

    INDEX
    Explanations

    of parent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    愚
    0.42
     CallbackContext
    0.40
     Marlin
    0.40
    哧
    0.39
     Sdn
    0.39
     kenapa
    0.39
     ké
    0.38
    FindingsResponse
    0.38
     Cantonese
    0.37
    店内
    0.37
    POSITIVE LOGITS
    pire
    0.44
    澥
    0.39
    ཙ
    0.38
     ricerc
    0.38
     बेंच
    0.36
    converter
    0.36
    examined
    0.35
    getObject
    0.35
     checks
    0.35
     во
    0.34
    Act Density 0.003%

    No Known Activations