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

    Neuronpedia

    INDEX
    Explanations

    #include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ○
    -0.07
     요청
    -0.07
     chú
    -0.07
     객체
    -0.07
    _department
    -0.06
     leur
    -0.06
    .paint
    -0.06
     duly
    -0.06
     superintendent
    -0.06
     κό
    -0.06
    POSITIVE LOGITS
     converge
    0.07
     convergence
    0.06
    qua
    0.06
     tweak
    0.06
     disturb
    0.06
    (sub
    0.06
    (NS
    0.06
    .�
    0.06
    -moving
    0.06
     predict
    0.06
    Act Density 0.012%

    No Known Activations