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

    Neuronpedia

    INDEX
    Explanations

    concepts related to political arguments and critiques

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

    "it" as a sentence subject followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    it is or would be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apunov
    -0.62
     étoit
    -0.56
     mempengaruhi
    -0.55
     فريبيس
    -0.53
     Konk
    -0.52
     permettra
    -0.51
     étoient
    -0.50
     påvir
    -0.49
    quelize
    -0.49
    numerusform
    -0.48
    POSITIVE LOGITS
     hardly
    0.70
     sma
    0.70
     smacked
    0.67
     sounds
    0.61
     ujednoznacz
    0.59
     raises
    0.59
    voyer
    0.59
     mögen
    0.59
     probably
    0.59
     recall
    0.58
    Act Density 0.484%

    No Known Activations