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

    Neuronpedia

    INDEX
    Explanations

    German language related words and sentence components

    oai_token-act-pair · gemini-2.0-flash

    war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.85
    ITERATURE
    -0.85
    脚注の使い方
    -0.85
    ^(@)
    -0.81
    %";
    -0.81
    %");
    -0.80
    arangay
    -0.79
    ','#
    -0.79
    ientras
    -0.79
    Amicalement
    -0.79
    POSITIVE LOGITS
    ,
    0.60
    ↵
    0.60
     with
    0.59
    <
    0.57
    ...
    0.56
    (
    0.56
    EndContext
    0.55
    \
    0.54
    .
    0.54
     much
    0.53
    Act Density 0.157%

    No Known Activations