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

    Neuronpedia

    INDEX
    Explanations

    Code, logs, or data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EL
    -0.07
    Uint
    -0.07
    educt
    -0.07
    ⚗
    -0.07
    elor
    -0.07
    ounc
    -0.07
    etch
    -0.06
    xFF
    -0.06
    绵阳
    -0.06
     essen
    -0.06
    POSITIVE LOGITS
     marty
    0.07
    (trans
    0.07
    (before
    0.07
    冰箱
    0.07
    最好是
    0.06
    black
    0.06
    -choice
    0.06
     VPN
    0.06
    ᛅ
    0.06
    띈
    0.06
    Act Density 0.472%

    No Known Activations