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

    Neuronpedia

    INDEX
    Explanations

    wording

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    徐
    -0.06
    اکم
    -0.06
    .psi
    -0.06
    ux
    -0.06
     знов
    -0.06
     simulate
    -0.06
    νομ
    -0.06
     plut
    -0.06
     utilization
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     BTC
    0.07
     پس
    0.07
    (dialog
    0.06
    _NON
    0.06
     MANUAL
    0.06
    ่องเท
    0.06
    elight
    0.06
     dine
    0.06
    encoding
    0.06
    _assigned
    0.06
    Act Density 0.000%

    No Known Activations