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

    Neuronpedia

    INDEX
    Explanations

    bandwidth/width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proxy
    -0.07
     identity
    -0.06
     внимание
    -0.06
     Masks
    -0.06
    .DESC
    -0.06
    FormData
    -0.06
     Be
    -0.06
    bar
    -0.06
    (pipe
    -0.06
     bounce
    -0.06
    POSITIVE LOGITS
    ा।
    0.08
    isme
    0.07
    ционных
    0.07
    �
    0.07
    Compra
    0.07
    ów
    0.06
    хран
    0.06
     genus
    0.06
    rowse
    0.06
    ул
    0.06
    Act Density 0.007%

    No Known Activations