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

    Neuronpedia

    INDEX
    Explanations

    37

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    8
    -0.08
    ac
    -0.07
     　　　　　
    -0.07
    especially
    -0.07
    210
    -0.07
     Advance
    -0.06
    SX
    -0.06
    ‌
    -0.06
     padx
    -0.06
    20
    -0.06
    POSITIVE LOGITS
    37
    0.39
    037
    0.11
    370
    0.09
    33
    0.07
    697
    0.07
    371
    0.07
    36
    0.07
     порт
    0.07
    (tid
    0.06
    directories
    0.06
    Act Density 0.005%

    No Known Activations