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

    Neuronpedia

    INDEX
    Explanations

    specific types or categories of objects being described

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

    type of sort requested

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MessageState
    -0.57
     itſelf
    -0.53
     препратки
    -0.52
     Anſ
    -0.51
    TextHelper
    -0.50
     Paglinawan
    -0.50
    ſelf
    -0.49
    ſcher
    -0.49
    JspWriter
    -0.49
    leyball
    -0.49
    POSITIVE LOGITS
     типа
    0.41
     con
    0.38
    expandindo
    0.37
     typu
    0.36
     type
    0.36
    ResumeLayout
    0.35
    ศ
    0.35
     Blech
    0.34
     tal
    0.33
     للمعارف
    0.33
    Act Density 0.043%

    No Known Activations