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

    Neuronpedia

    INDEX
    Explanations

    bullet points or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     궁금
    0.44
    inas
    0.44
    .
    0.44
    0.43
    0.41
     converg
    0.40
    ids
    0.39
    inuous
    0.39
     ดัง
    0.39
    ise
    0.38
    POSITIVE LOGITS
    🏾
    0.52
     Alhaji
    0.48
     Judah
    0.47
     AMAZING
    0.46
     Boko
    0.46
    éon
    0.45
    𝗢
    0.45
    ظيم
    0.44
    aisseur
    0.44
     súper
    0.44
    Act Density 0.006%

    No Known Activations