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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KL
    -0.09
     KL
    -0.09
     Kurt
    -0.08
     checkpoint
    -0.08
    ieder
    -0.08
     inactivity
    -0.08
     प्रक्रिया
    -0.08
     kl
    -0.07
     процесс
    -0.07
     situado
    -0.07
    POSITIVE LOGITS
    Ass
    0.10
    yes
    0.10
    fy
    0.10
    qq
    0.10
    y
    0.10
    ass
    0.09
    vara
    0.09
     assum
    0.08
    qy
    0.08
     Assume
    0.08
    Act Density 0.001%

    No Known Activations