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

    Neuronpedia

    INDEX
    Explanations

    processes starting or continuing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beginPath
    0.44
    宗
    0.44
    latin
    0.44
    us
    0.42
    清
    0.42
    מת
    0.42
    すべての
    0.42
    鹽
    0.42
     تمامی
    0.41
     lambda
    0.41
    POSITIVE LOGITS
     knocked
    0.48
     fairs
    0.48
     littoral
    0.47
     Miramar
    0.47
     hooded
    0.47
     hola
    0.47
     memorabilia
    0.47
     shoreline
    0.47
     predomin
    0.46
     clumps
    0.46
    Act Density 0.001%

    No Known Activations