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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uracy
    -0.06
     rights
    -0.06
    <g
    -0.06
    oods
    -0.06
    Currency
    -0.06
     heat
    -0.06
     who
    -0.06
    join
    -0.06
    Odd
    -0.06
     Nazi
    -0.06
    POSITIVE LOGITS
    <?=$
    0.06
    _markup
    0.06
     findet
    0.06
    /XML
    0.06
    '];
↵
↵
    0.06
    .asarray
    0.06
    .getExternalStorage
    0.06
     probs
    0.06
    %%↵
    0.06
    (mat
    0.06
    Act Density 0.054%

    No Known Activations