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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    251
    -0.07
    .shtml
    -0.07
    _config
    -0.06
    alaxy
    -0.06
    aukee
    -0.06
    osa
    -0.06
    umptech
    -0.06
    soap
    -0.06
    esch
    -0.06
    _te
    -0.06
    POSITIVE LOGITS
     шляхом
    0.07
    aysia
    0.06
    руб
    0.06
     proceeded
    0.06
     zákona
    0.06
     [],
↵
    0.06
     Swarm
    0.06
    tern
    0.06
     Anth
    0.06
    entence
    0.06
    Act Density 0.023%

    No Known Activations