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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     technique
    -0.07
     их
    -0.07
    Tester
    -0.07
    леч
    -0.06
    ter
    -0.06
     seeds
    -0.06
     Offset
    -0.06
     Sampling
    -0.06
     neighbours
    -0.06
     notamment
    -0.06
    POSITIVE LOGITS
    rasing
    0.07
    EDIT
    0.07
    estatus
    0.07
    resp
    0.06
    DateString
    0.06
     крок
    0.06
    amura
    0.06
     Hệ
    0.06
    ész
    0.06
    edit
    0.06
    Act Density 0.051%

    No Known Activations