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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ld
    -0.06
     �
    -0.06
     δύ
    -0.06
    شتر
    -0.06
    луж
    -0.06
    phem
    -0.06
    redentials
    -0.06
     punching
    -0.06
     picnic
    -0.06
    ritos
    -0.06
    POSITIVE LOGITS
    وران
    0.07
     Rein
    0.07
     toDate
    0.07
     phương
    0.06
    _ignore
    0.06
    夫人
    0.06
    협
    0.06
     ########.
    0.06
     através
    0.06
    чики
    0.06
    Act Density 0.024%

    No Known Activations