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

    Neuronpedia

    INDEX
    Explanations

    numerical values and data structures

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

    Characters followed by "idx"

    np_acts-logits-general · gemini-2.0-flash

    comma followed by idx

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.74
     Concordia
    -0.72
    iana
    -0.70
     Aryan
    -0.69
    rungsseite
    -0.69
    ValueStyle
    -0.65
    AccessorTable
    -0.64
     chanh
    -0.63
    EDEFAULT
    -0.63
     Martine
    -0.63
    POSITIVE LOGITS
    Slot
    0.85
     Slot
    0.81
     slot
    0.77
    delta
    0.76
    slot
    0.73
     Locke
    0.72
     Sz
    0.72
     Mackay
    0.70
     Hoff
    0.67
     McClellan
    0.66
    Act Density 0.726%

    No Known Activations