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

    Neuronpedia

    INDEX
    Explanations

    instructions and outcomes related to completing tasks or processes

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

    sequence or time

    np_acts-logits-general · gemini-2.0-flash

    afterward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reactivity
    -0.48
    RTLD
    -0.45
     zaman
    -0.45
    cade
    -0.44
    ),"
    -0.44
     inspiradoras
    -0.44
    >{@
    -0.43
    **/
    -0.43
    ⌋
    -0.43
     "'",
    -0.42
    POSITIVE LOGITS
     afterward
    0.76
     after
    0.75
     afterwards
    0.73
     baada
    0.67
     etter
    0.67
     після
    0.67
     quedado
    0.65
    after
    0.65
    setattr
    0.64
     usai
    0.63
    Act Density 0.246%

    No Known Activations