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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udson
    -0.07
    iêu
    -0.07
    itant
    -0.06
    模板
    -0.06
     fram
    -0.06
    主导
    -0.06
    处处长
    -0.06
    🚵
    -0.06
    빅
    -0.06
    Independent
    -0.06
    POSITIVE LOGITS
     اللغة
    0.08
    PLOY
    0.07
     PLAYER
    0.07
    eligible
    0.07
    .createParallelGroup
    0.07
    uniq
    0.07
     Pixels
    0.07
    chia
    0.07
     roam
    0.07
     Worldwide
    0.06
    Act Density 0.041%

    No Known Activations