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

    Neuronpedia

    INDEX
    Explanations

    repetitive expressions of certainty and affirmation

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

    going to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.84
     فريبيس
    -0.75
     propOrder
    -0.72
    bootstrapcdn
    -0.69
     ujednoznacz
    -0.69
     disambiguazione
    -0.68
    tagHelperRunner
    -0.65
     MainAxisSize
    -0.65
     dAtA
    -0.63
    󠀠
    -0.62
    POSITIVE LOGITS
    .”
    0.33
     ſtre
    0.32
    ,"
    0.32
    ```
    0.30
    REA
    0.30
     [
    0.29
    ."
    0.29
    ##############
    0.29
    []"
    0.29
    play
    0.28
    Act Density 0.031%

    No Known Activations