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

    Neuronpedia

    INDEX
    Explanations

    improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ikon
    -0.07
    زة
    -0.07
    aston
    -0.06
    �
    -0.06
     gang
    -0.06
     �
    -0.06
    agic
    -0.06
     Fakült
    -0.06
     projectile
    -0.06
    ляют
    -0.06
    POSITIVE LOGITS
     improvement
    0.09
     enhancements
    0.08
     amendments
    0.07
     emacs
    0.07
     cuatro
    0.07
     mour
    0.07
     Improvement
    0.07
     amendment
    0.07
    Audio
    0.07
    ------------↵
    0.06
    Act Density 0.018%

    No Known Activations