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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JNI
    -0.07
     Summary
    -0.07
    obs
    -0.07
     textbooks
    -0.07
    ulsion
    -0.07
    澌
    -0.07
    ccb
    -0.07
     excell
    -0.06
    (jj
    -0.06
    ṝ
    -0.06
    POSITIVE LOGITS
     WAIT
    0.08
     Center
    0.07
     HAR
    0.07
    樂
    0.07
     плит
    0.07
    🗨
    0.07
    놋
    0.06
    想象力
    0.06
     NYC
    0.06
    💒
    0.06
    Act Density 0.014%

    No Known Activations