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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document

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

    Text before question marks

    np_acts-logits-general · gemini-2.0-flash

    non-english words and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -0.68
     kaarangay
    -0.67
    GraphicsUnit
    -0.64
    jface
    -0.62
     purpoſe
    -0.59
    lapsingToolbar
    -0.56
    WO
    -0.56
     ſta
    -0.56
     uſed
    -0.54
     diſt
    -0.54
    POSITIVE LOGITS
    +#+
    0.62
    ########.
    0.53
    Tracce
    0.51
    ntgen
    0.51
     թվական
    0.50
    rrggbb
    0.50
     الدولى
    0.49
    ppens
    0.48
     Hunting
    0.48
     חיצוניים
    0.47
    Act Density 0.016%

    No Known Activations