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

    Neuronpedia

    INDEX
    Explanations

    context and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kõ
    0.47
    フ
    0.46
    ochemical
    0.45
    existence
    0.45
    賑
    0.44
     kogu
    0.44
    กระ
    0.43
     ज़र
    0.43
    シ
    0.42
    儼
    0.42
    POSITIVE LOGITS
    情况下
    0.38
     three
    0.38
    顺利
    0.37
     passcode
    0.37
     entries
    0.37
     cú
    0.37
     bốn
    0.37
    بلغ
    0.36
     And
    0.36
    三个
    0.34
    Act Density 0.001%

    No Known Activations