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

    Neuronpedia

    INDEX
    Explanations

    visible or invisible marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    नीचर
    1.69
     kehnd
    1.62
    ,\,
    1.51
     declaraciones
    1.50
    ,_
    1.48
     вікісторінку
    1.47
    lur
    1.46
     entrevistas
    1.44
    詞
    1.43
     documentación
    1.43
    POSITIVE LOGITS
    as
    1.35
    in
    1.07
    aber
    1.05
    amit
    1.05
     .
    1.03
     ecosystem
    1.03
    ”.
    1.02
    !!.
    1.00
     than
    1.00
    h
    0.98
    Act Density 0.000%

    No Known Activations