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

    Neuronpedia

    INDEX
    Explanations

    code snippets, data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahir
    -0.08
     abrir
    -0.07
    €
    -0.07
    /player
    -0.07
     taxable
    -0.07
    Det
    -0.06
    -any
    -0.06
     Cup
    -0.06
    NET
    -0.06
    aled
    -0.06
    POSITIVE LOGITS
     searchText
    0.06
    <div
    0.06
    esc
    0.06
     возраста
    0.06
    reb
    0.06
    aghan
    0.06
    　 　 　 　
    0.06
    (trim
    0.06
    accuracy
    0.05
    )."
    0.05
    Act Density 0.672%

    No Known Activations