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

    Neuronpedia

    INDEX
    Explanations

    legal rulings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
    ouncer
    -0.06
    观看
    -0.06
     ousted
    -0.06
    /lo
    -0.06
     Xu
    -0.06
    iate
    -0.06
    (mu
    -0.06
    omu
    -0.06
    enschaft
    -0.05
    POSITIVE LOGITS
    αλλ
    0.07
    δος
    0.07
     biển
    0.07
    (pr
    0.07
    getResponse
    0.07
     stap
    0.06
    _charset
    0.06
    **
↵
    0.06
     '".
    0.06
    /;↵
    0.06
    Act Density 0.008%

    No Known Activations