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

    Neuronpedia

    INDEX
    Explanations

    data loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     treaties
    -0.07
    후
    -0.06
     Farms
    -0.06
     things
    -0.06
    _floor
    -0.06
     conquer
    -0.06
    Trader
    -0.06
    Freedom
    -0.06
     뒤
    -0.06
    MOOTH
    -0.06
    POSITIVE LOGITS
     OnTrigger
    0.06
     yOffset
    0.06
    .AppCompatActivity
    0.06
    abcdefghijkl
    0.06
     Phys
    0.06
    >()↵
    0.06
     compens
    0.06
    .isHidden
    0.06
    ﾑ
    0.06
    .:.:.
    0.06
    Act Density 0.042%

    No Known Activations