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

    Neuronpedia

    INDEX
    Explanations

    say "touch"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ether
    -0.08
    reiben
    -0.07
     SSA
    -0.07
    ledged
    -0.07
     Boone
    -0.07
     LICENSE
    -0.07
     Oklahoma
    -0.07
    <Vec
    -0.07
     świe
    -0.06
     authors
    -0.06
    POSITIVE LOGITS
     cuid
    0.07
    市长
    0.07
    net
    0.06
    天气
    0.06
     vücud
    0.06
    办
    0.06
    ลด
    0.06
     missions
    0.06
    體驗
    0.06
    دو
    0.06
    Act Density 0.053%

    No Known Activations