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

    Neuronpedia

    INDEX
    Explanations

    explaining or clarifying concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вара
    0.48
    ور
    0.47
    Camping
    0.47
    一声
    0.47
    েকে
    0.47
    邮件
    0.46
    一切
    0.46
    íb
    0.46
    一点
    0.45
    страницу
    0.45
    POSITIVE LOGITS
     whale
    0.43
     Jerusalem
    0.41
     Scol
    0.41
     widowed
    0.40
     redox
    0.40
     wine
    0.40
     Mesmo
    0.40
     estim
    0.40
     rind
    0.39
     센
    0.39
    Act Density 0.002%

    No Known Activations