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

    Neuronpedia

    INDEX
    Explanations

    actor names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     checksum
    -0.06
    ANTS
    -0.06
    elong
    -0.06
     sweeping
    -0.06
     placeholder
    -0.06
     migraine
    -0.06
    learning
    -0.06
    محمد
    -0.06
     ER
    -0.06
    %timeout
    -0.06
    POSITIVE LOGITS
     estate
    0.09
     LGBT
    0.07
     release
    0.06
    antaged
    0.06
     yere
    0.06
    trib
    0.06
    _href
    0.06
     ді
    0.06
     رئیس
    0.06
     cripp
    0.06
    Act Density 0.128%

    No Known Activations