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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to various devices and their functionalities

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

    preceding "can" or "are"

    np_acts-logits-general · gemini-2.0-flash

    generally types of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的就是
    -0.33
    toggler
    -0.32
    UnusedPrivate
    -0.30
     activa
    -0.30
    ご了承
    -0.29
     jo
    -0.29
     دیکھیے
    -0.29
    rungsseite
    -0.28
     Its
    -0.28
    ád
    -0.28
    POSITIVE LOGITS
     generally
    0.96
     typically
    0.88
     geralmente
    0.87
    generally
    0.84
     généralement
    0.82
     generalmente
    0.81
     umumnya
    0.81
     often
    0.79
     usually
    0.77
     zwykle
    0.73
    Act Density 0.565%

    No Known Activations