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

    Neuronpedia

    INDEX
    Explanations

    definitions and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encompassing
    1.24
    𝐭
    1.07
    𝐠
    1.07
     arbitrary
    1.06
    𝐟
    1.04
    值为
    1.03
    тей
    1.02
    𝐩
    1.02
     Essentially
    1.02
    tare
    1.02
    POSITIVE LOGITS
    en
    1.08
    ه
    1.07
     fenómeno
    1.06
    ی
    1.04
    ी
    1.03
     procedimiento
    1.01
    ો
    1.01
     importância
    1.00
     phénomènes
    0.99
    eners
    0.98
    Act Density 0.005%

    No Known Activations