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

    Neuronpedia

    INDEX
    Explanations

    emojis following text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     denoting
    0.33
     hexadecimal
    0.31
    畋
    0.30
     hinch
    0.29
    achricht
    0.29
    utables
    0.29
     accesses
    0.28
     delegations
    0.28
     commands
    0.28
    䫒
    0.28
    POSITIVE LOGITS
    ħ
    0.30
    õ
    0.28
     ニ
    0.28
    쥐
    0.27
     ღ
    0.27
    本人
    0.27
     외
    0.27
    ių
    0.27
    回来
    0.26
     கணி
    0.26
    Act Density 0.003%

    No Known Activations