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

    Neuronpedia

    INDEX
    Explanations

    accusations and criticism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ula
    -0.07
    \modules
    -0.06
     CPA
    -0.06
    \Base
    -0.06
    rec
    -0.06
     Whe
    -0.06
     quarterly
    -0.06
    forc
    -0.06
     собою
    -0.06
    鼓
    -0.06
    POSITIVE LOGITS
     experimenting
    0.06
    BG
    0.06
    veedor
    0.06
     unconventional
    0.06
     bottoms
    0.06
    占
    0.06
     Crisis
    0.06
     kings
    0.06
     '#
    0.06
    //*[
    0.06
    Act Density 0.029%

    No Known Activations