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

    Neuronpedia

    INDEX
    Explanations

    length

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evils
    -0.07
     insn
    -0.07
    ップ
    -0.07
    喻
    -0.07
     invariably
    -0.07
     нормальн
    -0.06
    �
    -0.06
     histoire
    -0.06
    好坏
    -0.06
     mobs
    -0.06
    POSITIVE LOGITS
    cooldown
    0.07
    (local
    0.07
    gebn
    0.07
    Portal
    0.06
     liquidity
    0.06
     Computing
    0.06
    Civil
    0.06
     NGO
    0.06
    ט
    0.06
    ocket
    0.06
    Act Density 0.027%

    No Known Activations