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

    Neuronpedia

    INDEX
    Explanations

    treasure

    np_max-act · gemini-2.0-flash

    interactive elements and choices within narratives.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	append
    -0.06
    _receiver
    -0.06
     matches
    -0.06
    orias
    -0.06
    utdown
    -0.06
    ことが
    -0.06
    dv
    -0.06
     accounting
    -0.05
    ighbors
    -0.05
     arbitration
    -0.05
    POSITIVE LOGITS
    _ASSOC
    0.08
     Associ
    0.07
    vio
    0.07
    辦
    0.07
     hlavy
    0.07
    Impl
    0.07
    ––
    0.06
     tut
    0.06
     кіль
    0.06
     نه
    0.06
    Act Density 0.016%

    No Known Activations