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

    Neuronpedia

    INDEX
    Explanations

    principal components or reading comprehension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    戞
    0.80
    戝
    0.80
     Aula
    0.75
    ursor
    0.69
    yny
    0.67
    纭
    0.66
    ائر
    0.64
     காவல்துற
    0.64
    맺
    0.63
     council
    0.63
    POSITIVE LOGITS
     comp
    3.68
     COMP
    3.61
    Comp
    3.59
     Comp
    3.51
    COMP
    3.40
    comp
    3.35
     Kom
    3.34
     compon
    3.29
     component
    3.24
     컴
    3.17
    Act Density 0.601%

    No Known Activations