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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('<?
    -0.07
    _SHIFT
    -0.07
    tgl
    -0.07
    mongoose
    -0.07
     Vivo
    -0.06
     matriz
    -0.06
    keh
    -0.06
     đáng
    -0.06
    ửa
    -0.06
    ata
    -0.06
    POSITIVE LOGITS
    ธาน
    0.07
    .д
    0.07
     час
    0.06
     insightful
    0.06
     Phú
    0.06
     tastes
    0.06
     Afr
    0.06
    (Contact
    0.06
    (parts
    0.06
    един
    0.06
    Act Density 0.012%

    No Known Activations