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

    Neuronpedia

    INDEX
    Explanations

    code and document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Course
    -0.08
     amore
    -0.07
     сот
    -0.07
    (levels
    -0.07
     underage
    -0.07
     UserType
    -0.07
     路
    -0.06
     SSE
    -0.06
    벤트
    -0.06
     ś
    -0.06
    POSITIVE LOGITS
    conomic
    0.06
     Who
    0.06
    Rule
    0.06
     Cooperation
    0.06
    Disney
    0.06
     guns
    0.06
    Sexy
    0.06
    powers
    0.06
     automation
    0.06
    DOWN
    0.06
    Act Density 0.001%

    No Known Activations