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

    Neuronpedia

    INDEX
    Explanations

    key terms related to enabling, limiting, or asserting processes and their effects

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

    introducing or restricting actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.99
     Exacts
    -0.91
    -0.91
    enderror
    -0.90
     müſſen
    -0.89
     fashiola
    -0.88
    ロウィン
    -0.88
    <unused28>
    -0.87
    <unused23>
    -0.87
    <unused14>
    -0.87
    POSITIVE LOGITS
    si
    0.25
     In
    0.25
    ba
    0.23
     communiquer
    0.22
    .
    0.21
     vuelta
    0.21
    (
    0.19
     durumu
    0.19
      
    0.19
    â
    0.18
    Act Density 0.494%

    No Known Activations