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

    Neuronpedia

    INDEX
    Explanations

    quantized models or media states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вая
    0.45
    듭
    0.45
    жив
    0.44
     другие
    0.44
    ್ಣ
    0.44
    lastval
    0.43
    ъм
    0.42
    ਦ
    0.42
     фина
    0.42
    ាន់
    0.42
    POSITIVE LOGITS
     من
    0.49
     from
    0.47
     on
    0.47
     barista
    0.46
     in
    0.44
     hijab
    0.44
     off
    0.43
     dễ
    0.42
     Chameleon
    0.42
    出现在
    0.42
    Act Density 0.017%

    No Known Activations