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

    Neuronpedia

    INDEX
    Explanations

    manuscript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Logged
    -0.07
     *)"
    -0.06
    ｀ヽ
    -0.06
    मह
    -0.06
    陶
    -0.06
    WINDOW
    -0.06
    Sadly
    -0.06
     skeptic
    -0.06
    -standing
    -0.06
    :');↵
    -0.06
    POSITIVE LOGITS
    動
    0.07
    icism
    0.07
    -next
    0.07
    ír
    0.07
    angan
    0.06
     conf
    0.06
     FC
    0.06
    ENSITY
    0.06
     Gee
    0.06
     isi
    0.06
    Act Density 0.013%

    No Known Activations