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

    Neuronpedia

    INDEX
    Explanations

    explain specific questions or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    χρι
    0.50
    𝔞
    0.49
    さまざ
    0.48
    をする
    0.47
    ཥ
    0.46
    σα
    0.46
    まい
    0.46
    지털
    0.46
    τζ
    0.45
    ようだ
    0.45
    POSITIVE LOGITS
    information
    0.47
     abandoning
    0.47
    ii
    0.47
    en
    0.46
    is
    0.46
    country
    0.46
     Review
    0.45
     comments
    0.44
     بيانات
    0.44
    comment
    0.44
    Act Density 0.001%

    No Known Activations