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

    Neuronpedia

    INDEX
    Explanations

    spanning millions of years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    マータイヤ
    0.60
     puris
    0.51
     Elec
    0.50
     grooves
    0.48
    yesters
    0.48
     Excise
    0.47
    átiles
    0.47
     ETFs
    0.46
    ကိုယ်
    0.46
     Agricult
    0.46
    POSITIVE LOGITS
    indan
    0.41
     ટુ
    0.41
    CN
    0.41
    5
    0.40
    KeyboardMarkup
    0.39
     ppl
    0.39
    4
    0.39
    1
    0.39
    ice
    0.38
     hab
    0.38
    Act Density 0.000%

    No Known Activations