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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    出品
    -0.06
     установки
    -0.06
    उत
    -0.06
    男子
    -0.06
     Foster
    -0.06
     Stephens
    -0.06
     Casual
    -0.06
     Side
    -0.06
     courte
    -0.05
     empath
    -0.05
    POSITIVE LOGITS
     trig
    0.07
    rium
    0.07
    -view
    0.07
    Matches
    0.06
     opcode
    0.06
    šku
    0.06
    点击
    0.06
    .''
    0.06
    (rate
    0.06
     kissing
    0.06
    Act Density 0.051%

    No Known Activations