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

    Neuronpedia

    INDEX
    Explanations

    names of authors and characters related to specific literary works

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

    names of people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compito
    -0.41
     peito
    -0.41
    pulumi
    -0.37
    fscanf
    -0.36
    ntry
    -0.35
    jbl
    -0.33
    /**
    -0.33
    netinet
    -0.33
    culada
    -0.33
     Dijo
    -0.32
    POSITIVE LOGITS
     للاسماء
    0.91
     Dublin
    0.67
     Irishman
    0.60
    Dublin
    0.58
     Irish
    0.54
     Ireland
    0.52
     Ulysses
    0.52
     Chwiliwch
    0.49
     nakalista
    0.49
     surla
    0.49
    Act Density 0.031%

    No Known Activations