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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᄒ
    -0.07
     '*.
    -0.07
     michael
    -0.07
     הזוג
    -0.06
     hoops
    -0.06
    _store
    -0.06
     למצוא
    -0.06
    Na
    -0.06
    зо
    -0.06
    Wy
    -0.06
    POSITIVE LOGITS
    ."',
    0.08
     culturally
    0.08
    辜负
    0.07
     revital
    0.07
    不知不觉
    0.07
     campaigns
    0.07
     Introduction
    0.07
    尤其
    0.07
    我一直
    0.07
    ày
    0.07
    Act Density 0.035%

    No Known Activations