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

    Neuronpedia

    INDEX
    Explanations

    no warranty of any kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kindern
    0.44
    簹
    0.44
    isterschaft
    0.43
     ordinateur
    0.42
     လ
    0.42
    Hero
    0.41
    เด็ก
    0.41
     간단
    0.41
     देखील
    0.41
    issenschaft
    0.40
    POSITIVE LOGITS
    (,
    0.44
    [,]
    0.43
    ,”
    0.43
    ,'
    0.42
     IPA
    0.42
    [,
    0.41
     whatsoever
    0.41
    мию
    0.41
    ală
    0.41
     čak
    0.40
    Act Density 0.001%

    No Known Activations