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

    Neuronpedia

    INDEX
    Explanations

    hot and warm concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ర్రీ
    0.70
    Hearing
    0.67
    किट
    0.66
     जीवन
    0.66
    aneers
    0.65
    riterion
    0.64
    ರ್‌
    0.64
    اتها
    0.64
    hala
    0.64
     chefe
    0.63
    POSITIVE LOGITS
     temperatures
    1.27
    blooded
    1.07
     Temperatures
    1.07
     hot
    1.05
    hot
    1.05
     Temperaturen
    1.03
     Hot
    1.01
    🥵
    1.01
    eliers
    1.00
    ♨
    0.99
    Act Density 0.165%

    No Known Activations