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

    Neuronpedia

    INDEX
    Explanations

    call to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     기간
    1.31
    og
    1.27
     be
    1.27
    noon
    1.24
    decks
    1.22
    ត្រូ
    1.21
     crisi
    1.20
    闩
    1.19
    doing
    1.18
    rifice
    1.16
    POSITIVE LOGITS
    و
    1.82
    ா
    1.36
    ல்
    1.33
     ballpark
    1.24
    यें
    1.23
    อร์
    1.21
     inadequ
    1.21
    κα
    1.20
    لون
    1.20
    lena
    1.20
    Act Density 0.001%

    No Known Activations