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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong admiration or fandom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expresses liking or admiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.59
    HandlerContext
    -0.54
    nextProps
    -0.50
     mxArray
    -0.49
     незавершена
    -0.49
    complexContent
    -0.49
     Administrativna
    -0.46
    ✢
    -0.45
    VITA
    -0.45
    tilus
    -0.45
    POSITIVE LOGITS
     gostar
    0.54
     gustaba
    0.54
     proponent
    0.49
     recomendar
    0.48
     gustan
    0.48
     admirer
    0.48
     gillar
    0.47
     favoritos
    0.45
     khảo
    0.45
     favored
    0.45
    Act Density 0.005%

    No Known Activations