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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pes
    -0.07
     klient
    -0.06
     Describe
    -0.06
     خلق
    -0.06
     ailments
    -0.06
     обуч
    -0.06
    meniz
    -0.06
    plusplus
    -0.06
    (dto
    -0.06
     uomo
    -0.06
    POSITIVE LOGITS
    하며
    0.08
     Buchanan
    0.06
    765
    0.06
    642
    0.06
    即
    0.06
     Rodriguez
    0.06
    210
    0.06
    027
    0.06
    .green
    0.06
     Belt
    0.06
    Act Density 0.000%

    No Known Activations