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

    Neuronpedia

    INDEX
    Explanations

    improvement in quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    є
    0.55
    ิด
    0.51
     sexism
    0.48
     classe
    0.47
    咙
    0.47
    บคุม
    0.47
    ні
    0.46
     neuropathy
    0.46
    вається
    0.46
    وی
    0.46
    POSITIVE LOGITS
     እን
    0.55
     Invit
    0.47
    rowave
    0.47
     شعر
    0.46
    𝒟
    0.45
     美
    0.45
    បំ
    0.45
     طبق
    0.44
     அங்க
    0.44
    }^{*}=
    0.44
    Act Density 0.000%

    No Known Activations