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

    Neuronpedia

    INDEX
    Explanations

    filter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cube
    -0.08
     obsahuje
    -0.07
     古
    -0.06
     formation
    -0.06
     mascot
    -0.06
     появи
    -0.06
     přist
    -0.06
    Nil
    -0.06
    VERTISE
    -0.06
     контак
    -0.06
    POSITIVE LOGITS
    lf
    0.06
    deployment
    0.06
    -bal
    0.06
    ิญญ
    0.06
    */↵↵↵
    0.06
     lstm
    0.06
    _fw
    0.06
    ucumber
    0.06
     GAL
    0.06
     Selection
    0.06
    Act Density 0.003%

    No Known Activations