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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and expressions of frustration or discomfort

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

    Punctuation, especially periods and question marks

    np_acts-logits-general · gemini-2.0-flash

    by changing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.83
     незавершена
    -0.78
    setupUi
    -0.69
    AndEndTag
    -0.68
    bootstrapcdn
    -0.67
    Kaynakça
    -0.67
    NUMX
    -0.67
    ^(@)
    -0.67
     CreateTagHelper
    -0.66
     Chwiliwch
    -0.64
    POSITIVE LOGITS
    After
    0.57
    !
    0.53
     After
    0.53
     !
    0.50
    Moreover
    0.49
     farsi
    0.49
    heiser
    0.49
     jälkeen
    0.48
    違います
    0.48
    Even
    0.47
    Act Density 0.033%

    No Known Activations