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

    Neuronpedia

    INDEX
    Explanations

    directives or prompts for user input

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

    enter or そこで

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beroep
    -0.43
     déchir
    -0.42
     compétence
    -0.41
     alimentaria
    -0.41
     Gouvernement
    -0.40
     comunista
    -0.40
     mourir
    -0.39
    lidad
    -0.39
     betrekking
    -0.39
     Juifs
    -0.39
    POSITIVE LOGITS
     Enter
    1.13
    Enter
    1.02
     enter
    0.85
     ENTER
    0.83
     entered
    0.75
    ENTER
    0.75
    MigrationBuilder
    0.73
     Entered
    0.73
    entered
    0.71
     enters
    0.70
    Act Density 0.006%

    No Known Activations