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

    Neuronpedia

    INDEX
    Explanations

    specific geographical locations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Location or institution names

    np_acts-logits-general · gemini-2.0-flash

    named places and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     often
    -0.30
     sign
    -0.30
     self
    -0.30
     direct
    -0.30
     disturbance
    -0.29
     
    -0.28
    self
    -0.28
     usein
    -0.28
    ORN
    -0.28
     сто
    -0.28
    POSITIVE LOGITS
    Referanser
    0.66
     autorytatywna
    0.64
    ########.
    0.61
     nonUne
    0.60
    Чыгана
    0.60
     geweſen
    0.60
     ſeyn
    0.59
     müſſen
    0.59
     verſch
    0.59
    Manbalar
    0.59
    Act Density 0.465%

    No Known Activations