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

    Neuronpedia

    INDEX
    Explanations

    interle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CascadeType
    -0.07
    inox
    -0.07
    uard
    -0.07
    bnb
    -0.07
    فن
    -0.07
     baptized
    -0.07
    uros
    -0.07
    gages
    -0.07
    葆
    -0.07
    概
    -0.06
    POSITIVE LOGITS
    见效
    0.08
    ("\(
    0.07
    Automatic
    0.07
     Cro
    0.07
     Automatic
    0.07
    鲒
    0.07
     lst
    0.06
    *)
    0.06
    {}]
    0.06
     chol
    0.06
    Act Density 0.002%

    No Known Activations