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

    Neuronpedia

    INDEX
    Explanations

    thanos, thales, thassos, thonny

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Boards
    0.41
     conti
    0.40
    סת
    0.39
     toughest
    0.39
     sper
    0.39
    ‹
    0.37
    reg
    0.36
    Board
    0.36
    Pow
    0.36
     mancan
    0.36
    POSITIVE LOGITS
    েশন
    0.42
    ^{+}\
    0.40
    _{*}\
    0.40
     χαρακτη
    0.38
    শ্বর
    0.38
    ᱡ
    0.38
    hende
    0.37
     पीरियड
    0.37
    unicorn
    0.36
    helia
    0.36
    Act Density 0.003%

    No Known Activations