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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ducer
    -0.07
    atím
    -0.07
     vlád
    -0.06
     یافت
    -0.06
    oger
    -0.06
    ziel
    -0.06
    getStore
    -0.06
     OB
    -0.06
    Cube
    -0.06
     wholesalers
    -0.06
    POSITIVE LOGITS
    -name
    0.07
     Rather
    0.06
    .Next
    0.06
     Cannabis
    0.06
    向
    0.06
    实验
    0.06
    ようです
    0.06
     clinic
    0.06
     grated
    0.06
     vegetarian
    0.06
    Act Density 0.005%

    No Known Activations