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

    Neuronpedia

    INDEX
    Explanations

    values associated with ranking or ordering, particularly in a mathematical or comparative context

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

    Followed by "Let"

    np_acts-logits-general · gemini-2.0-flash

    b) option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    -0.70
    it
    -0.69
     Donahue
    -0.66
    ly
    -0.64
    in
    -0.64
     rest
    -0.63
    y
    -0.60
    at
    -0.59
    l
    -0.58
     Rest
    -0.56
    POSITIVE LOGITS
     bVar
    1.16
     UVB
    1.07
     getB
    1.06
     vPvB
    1.00
     DVB
    0.97
     YB
    0.96
     NTB
    0.95
     Ub
    0.95
    ViewInit
    0.95
    aab
    0.93
    Act Density 0.286%

    No Known Activations