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

    Neuronpedia

    INDEX
    Explanations

    HTML attributes for labels and accessibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هی
    0.44
    仑
    0.41
    溁
    0.39
    䣫
    0.39
    暇
    0.38
    ╿
    0.38
    ཀ
    0.37
    🍛
    0.37
    菘
    0.36
    稦
    0.36
    POSITIVE LOGITS
     disabled
    0.44
     aria
    0.39
    email
    0.39
     #
    0.38
    disabled
    0.38
     email
    0.36
    anal
    0.35
     co
    0.35
    aria
    0.35
     example
    0.35
    Act Density 0.004%

    No Known Activations