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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agh
    -0.07
     Beck
    -0.07
     known
    -0.07
     baked
    -0.06
    _END
    -0.06
    RAFT
    -0.06
     Spe
    -0.06
    -sale
    -0.06
     rightly
    -0.06
     gs
    -0.06
    POSITIVE LOGITS
     формування
    0.06
    sembly
    0.06
     můžete
    0.06
    olicy
    0.06
     постоян
    0.06
    bulan
    0.06
    (images
    0.06
    vehicle
    0.06
    ประถม
    0.06
     interle
    0.06
    Act Density 0.015%

    No Known Activations