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

    Neuronpedia

    INDEX
    Explanations

    animal research models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ابا
    0.57
    кті
    0.57
    ன்மை
    0.55
     pasan
    0.55
    amasını
    0.54
     миро
    0.54
    ارهای
    0.53
    ayutt
    0.53
    𒆳
    0.53
    ayatiti
    0.52
    POSITIVE LOGITS
     mice
    0.87
     rats
    0.77
     animals
    0.61
     mouse
    0.61
     rodents
    0.60
            
    0.58
     rabbits
    0.58
    mice
    0.55
    0.55
    mouse
    0.52
    Act Density 0.068%

    No Known Activations