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

    Neuronpedia

    INDEX
    Explanations

    GaussianBlur function call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hurling
    1.69
    ва
    1.63
    𝟙
    1.63
     Suriname
    1.60
    ॉकलेट
    1.58
     executable
    1.53
    >−</
    1.53
     drowning
    1.51
    (""))
    1.50
     leftovers
    1.48
    POSITIVE LOGITS
     بيانات
    1.83
    ﺀ
    1.54
    T
    1.54
    शियल
    1.51
     zejména
    1.50
    良好的
    1.50
    ຫາ
    1.50
    Highly
    1.48
    jelent
    1.46
     allgemeinen
    1.46
    Act Density 0.000%

    No Known Activations