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

    Neuronpedia

    INDEX
    Explanations

    evolution and pressure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     +
    1.22
     get
    1.18
     هم
    1.14
    と
    1.13
     good
    1.12
     お
    1.11
    1.10
    ents
    1.09
    >=
    1.09
     w
    1.08
    POSITIVE LOGITS
     météor
    1.21
     dwRes
    1.11
     nuovamente
    1.06
    addDigit
    1.04
    DVRIP
    1.04
    Ошибка
    1.03
     antioxid
    1.02
     Министерства
    1.01
    FileWriter
    1.00
    Ꮐ
    1.00
    Act Density 0.026%

    No Known Activations