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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical specifications and performance of devices

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

    Follows certain nouns

    np_acts-logits-general · gemini-2.0-flash

    OR REMOVE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Efq
    -0.99
     ―――――
    -0.90
     Majefty
    -0.89
    endphp
    -0.85
     myſelf
    -0.85
    ſelf
    -0.83
    ^(@)
    -0.82
     Савезне
    -0.80
     photolibrary
    -0.80
    ⋙
    -0.79
    POSITIVE LOGITS
     The
    1.63
     It
    1.51
     There
    1.38
     They
    1.29
    The
    1.23
    It
    1.18
     ,
    1.18
     Those
    1.16
     This
    1.12
    There
    1.08
    Act Density 0.019%

    No Known Activations