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

    Neuronpedia

    INDEX
    Explanations

    Road

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Un
    -0.07
     mont
    -0.07
     숨
    -0.07
    _Master
    -0.06
     recipients
    -0.06
    Nature
    -0.06
    <data
    -0.06
     clique
    -0.06
    _$
    -0.06
    _True
    -0.06
    POSITIVE LOGITS
    切
    0.07
    ativ
    0.06
     opens
    0.06
     mpl
    0.06
     Bison
    0.06
     repro
    0.06
    ));↵↵↵
    0.06
    響
    0.06
     retrie
    0.06
    .EXP
    0.06
    Act Density 0.000%

    No Known Activations