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

    Neuronpedia

    INDEX
    Explanations

    code or programming-related syntax or structures

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

    Mathematical or programming-related expressions

    np_acts-logits-general · gemini-2.0-flash

    structured data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recuerdos
    -0.49
    例句
    -0.49
     reminder
    -0.48
    اء
    -0.47
     ¿
    -0.45
     noticeably
    -0.45
     acuerdo
    -0.45
     види
    -0.45
     recuerdo
    -0.44
     noticed
    -0.44
    POSITIVE LOGITS
     '\\;'
    1.16
    Personendaten
    1.02
     intimately
    0.92
     myſelf
    0.89
     becauſe
    0.86
     firsthand
    0.83
     Bescheid
    0.83
    InputBorder
    0.81
    Geplaatst
    0.81
    expandindo
    0.80
    Act Density 0.252%

    No Known Activations