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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upscale
    -0.08
    Explore
    -0.07
     notch
    -0.07
     Ethiopian
    -0.06
    matter
    -0.06
    -equipped
    -0.06
    ed
    -0.06
    LinkedIn
    -0.06
    plash
    -0.06
     achieve
    -0.06
    POSITIVE LOGITS
     איל
    0.08
    lard
    0.07
     standard
    0.07
    yz
    0.07
    .badlogic
    0.07
    蓁
    0.07
     tokenId
    0.07
    ตร
    0.07
     Nicolas
    0.07
    惯
    0.07
    Act Density 0.001%

    No Known Activations