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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toJSON
    -0.06
    	lp
    -0.06
    amax
    -0.06
     enlarged
    -0.06
    �
    -0.06
    ΕΚ
    -0.06
    pra
    -0.05
    -0.05
    ляем
    -0.05
    аду
    -0.05
    POSITIVE LOGITS
    .Appearance
    0.08
     Reflection
    0.07
     birlik
    0.07
    ��
    0.07
     vytvoř
    0.07
     Θ
    0.07
    -groups
    0.07
     vagy
    0.07
    planation
    0.07
    (:,
    0.07
    Act Density 0.160%

    No Known Activations