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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hashlib
    -0.09
     banks
    -0.08
     Frozen
    -0.08
     Jeanne
    -0.07
     världen
    -0.07
     �
    -0.07
     Baking
    -0.07
     jie
    -0.07
     Worldwide
    -0.07
     frozen
    -0.07
    POSITIVE LOGITS
     spokesman
    0.09
     relevantes
    0.08
    Advertisements
    0.08
    He's
    0.08
     announces
    0.08
     ولن
    0.08
    కుండా
    0.08
    回复
    0.08
     einzigen
    0.07
    .rectangle
    0.07
    Act Density 0.004%

    No Known Activations