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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тож
    -0.08
    зм
    -0.07
     jeep
    -0.07
     rovněž
    -0.07
    _nl
    -0.07
    нев
    -0.06
     ninja
    -0.06
     hamm
    -0.06
    :black
    -0.06
     чор
    -0.06
    POSITIVE LOGITS
    651
    0.07
    525
    0.06
    因此
    0.06
     Lyons
    0.06
    Platform
    0.06
    ΕΚ
    0.06
    ££
    0.06
    DOMAIN
    0.06
    CA
    0.06
    —"
    0.06
    Act Density 0.000%

    No Known Activations