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

    Neuronpedia

    INDEX
    Explanations

    say "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λος
    -0.07
     "&#
    -0.07
    Words
    -0.07
    _version
    -0.07
    *=
    -0.07
    ?>><?
    -0.06
    ığı
    -0.06
     Đ
    -0.06
    _square
    -0.06
    Write
    -0.06
    POSITIVE LOGITS
     nan
    0.06
     Gran
    0.06
    -clean
    0.06
    -eng
    0.06
    _IMAGES
    0.06
     ngăn
    0.06
     contentious
    0.06
    �
    0.06
     hotelu
    0.06
     disabled
    0.06
    Act Density 0.040%

    No Known Activations