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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their related content

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

    prefix `and` `as` `or` `which` `for`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     The
    -0.44
     This
    -0.44
     Gegen
    -0.42
    AutoField
    -0.40
     gran
    -0.40
    olio
    -0.40
     single
    -0.40
     this
    -0.40
     Vorg
    -0.39
     Group
    -0.39
    POSITIVE LOGITS
     nakalista
    0.57
     myſelf
    0.56
    хьтан
    0.56
     reaſon
    0.51
     leaſt
    0.50
    ſelf
    0.49
     itſelf
    0.49
     Comprometido
    0.48
     fubject
    0.48
     juſ
    0.48
    Act Density 0.026%

    No Known Activations