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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "the."

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

    programs and initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.65
     noDo
    -0.48
     numberWith
    -0.46
     sneaky
    -0.46
    fjspx
    -0.46
     crooked
    -0.46
     blonde
    -0.43
    otone
    -0.42
     weird
    -0.42
    ArgsConstructor
    -0.42
    POSITIVE LOGITS
     programmet
    0.48
     programme
    0.43
    awtextra
    0.42
     programmi
    0.41
     program
    0.40
    計劃
    0.40
     initiative
    0.40
     community
    0.40
    计划
    0.39
    為主
    0.39
    Act Density 0.074%

    No Known Activations