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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Overview
    0.39
    Intensity
    0.38
     Wow
    0.38
    Au
    0.37
     Lice
    0.37
    상품
    0.37
    inine
    0.36
     Intensity
    0.36
     Au
    0.36
    Fn
    0.36
    POSITIVE LOGITS
     rjf
    0.45
    ที่เป็น
    0.44
     abc
    0.43
    <0xD9>
    0.43
    檜
    0.41
     Arap
    0.41
    ومه
    0.40
     !}
    0.40
    ୭
    0.39
     sawmill
    0.39
    Act Density 0.014%

    No Known Activations