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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esát
    -0.07
    吐
    -0.07
    atz
    -0.06
    ении
    -0.06
     �
    -0.06
     hast
    -0.06
     SVC
    -0.06
    क
    -0.06
     wag
    -0.06
    ated
    -0.06
    POSITIVE LOGITS
     jersey
    0.07
     Similarly
    0.06
    هر
    0.06
    vious
    0.06
    {|
    0.06
    /delete
    0.06
     nội
    0.06
    POSE
    0.06
     bás
    0.06
     noci
    0.06
    Act Density 0.139%

    No Known Activations