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

    Neuronpedia

    INDEX
    Explanations

    Romance/Fan fiction excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    我的
    -0.06
    classnames
    -0.06
     çocuğ
    -0.06
    -la
    -0.06
     Sites
    -0.06
    ampions
    -0.06
    -you
    -0.06
    attern
    -0.06
     ATTACK
    -0.06
    “What
    -0.06
    POSITIVE LOGITS
    =length
    0.06
    xlim
    0.06
    mam
    0.06
    력
    0.06
     SOC
    0.06
     prive
    0.06
    FOUND
    0.06
    面積
    0.06
    .getField
    0.06
    �果
    0.06
    Act Density 0.020%

    No Known Activations