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

    Neuronpedia

    INDEX
    Explanations

    is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ced
    0.42
    -<
    0.35
    nych
    0.34
    adi
    0.34
    ce
    0.34
    there
    0.34
    limit
    0.34
    adhi
    0.32
    pred
    0.32
    standard
    0.32
    POSITIVE LOGITS
    ர்த்தி
    0.42
    乱
    0.39
     äuß
    0.39
    uşt
    0.38
     ко
    0.38
    亂
    0.37
    कों
    0.37
     पसंदीदा
    0.37
     farms
    0.36
    共和
    0.36
    Act Density 0.002%

    No Known Activations