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

    Neuronpedia

    INDEX
    Explanations

    ocked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HT
    -0.07
    Bern
    -0.06
     Corinthians
    -0.06
     legalize
    -0.06
    .colorbar
    -0.06
     Writes
    -0.06
    "nil
    -0.06
    <$
    -0.06
    ув
    -0.06
    _form
    -0.06
    POSITIVE LOGITS
     harvested
    0.07
    ώς
    0.06
     réalis
    0.06
    bones
    0.06
     Kaynak
    0.06
     fashion
    0.06
     LIGHT
    0.06
     |
    0.06
     incididunt
    0.06
     格
    0.06
    Act Density 0.000%

    No Known Activations