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

    Neuronpedia

    INDEX
    Explanations

    switch to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    τες
    1.30
    ತನ
    1.24
    ɱ
    1.23
    OnInit
    1.21
    Julie
    1.18
    ్ఞ
    1.17
    ে
    1.17
     infirm
    1.17
     mischief
    1.16
     miscon
    1.14
    POSITIVE LOGITS
    y
    1.27
    Назад
    1.26
    ста
    1.24
     importance
    1.22
    م
    1.17
    iril
    1.16
    yf
    1.16
    вому
    1.14
    ഗ
    1.13
    えた
    1.13
    Act Density 0.112%

    No Known Activations