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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    .start
    -0.07
    .compare
    -0.07
    不停
    -0.07
    ivität
    -0.07
     Towards
    -0.07
     sólo
    -0.07
    ythm
    -0.07
    .enter
    -0.07
    .groups
    -0.07
    POSITIVE LOGITS
     xảy
    0.08
    zej
    0.08
     בת
    0.08
     netwerk
    0.08
     برج
    0.08
     facilitated
    0.08
     terjadi
    0.08
     upe
    0.07
     πό
    0.07
     ellen
    0.07
    Act Density 0.000%
    No Known Activations