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

    Neuronpedia

    INDEX
    Explanations

    micro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Saul
    -0.08
    ассив
    -0.07
    933
    -0.07
     heap
    -0.07
    .sess
    -0.07
     designers
    -0.07
     congen
    -0.07
     Sadd
    -0.06
    339
    -0.06
    idenav
    -0.06
    POSITIVE LOGITS
     Micro
    0.12
     micro
    0.11
    Micro
    0.09
     microwave
    0.09
    micro
    0.08
     Мик
    0.08
     microbes
    0.08
    metros
    0.08
     мик
    0.08
     Mik
    0.08
    Act Density 0.023%

    No Known Activations