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

    Neuronpedia

    INDEX
    Explanations

    Start of a story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rem
    -0.06
    respect
    -0.06
    yk
    -0.06
    _metadata
    -0.06
     edil
    -0.06
    �
    -0.06
    �
    -0.06
     Query
    -0.06
     masih
    -0.06
    дают
    -0.06
    POSITIVE LOGITS
     desperately
    0.07
    .Transfer
    0.07
     MISS
    0.07
    341
    0.07
    Publisher
    0.07
    -*-
    0.06
    (Product
    0.06
    ="'+
    0.06
     swinger
    0.06
    Absolutely
    0.06
    Act Density 0.057%

    No Known Activations