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

    Neuronpedia

    INDEX
    Explanations

    spaced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simpl
    -0.07
     rewards
    -0.07
     eventos
    -0.07
    🦌
    -0.07
    untas
    -0.07
    >e
    -0.07
    휜
    -0.07
    _DE
    -0.07
    落ち着
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Wife
    0.08
     [{↵
    0.07
    舅
    0.07
     stacked
    0.07
    Gary
    0.07
     apare
    0.07
     Date
    0.07
    Expiration
    0.07
    Province
    0.07
    国民经济
    0.07
    Act Density 0.006%

    No Known Activations