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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.62
    ".
    -0.62
    DebuggerNonUser
    -0.62
    )";
    -0.61
    .";
    -0.56
     ſmall
    -0.56
     Raim
    -0.54
     hdi
    -0.53
     Савезне
    -0.52
    Comté
    -0.52
    POSITIVE LOGITS
     '{@
    0.68
    #
    0.64
     Only
    0.63
    WriteBarrier
    0.56
    Only
    0.55
     only
    0.55
    риях
    0.54
    SPATH
    0.53
    Lugares
    0.52
     только
    0.51
    Act Density 0.004%

    No Known Activations