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

    Neuronpedia

    INDEX
    Explanations

    annealing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XB
    -0.06
     stru
    -0.06
     collaborate
    -0.06
     य
    -0.06
    -device
    -0.06
     Ulus
    -0.06
     disguised
    -0.06
     Ber
    -0.06
     право
    -0.06
    转
    -0.06
    POSITIVE LOGITS
    assage
    0.07
    ctrine
    0.06
    enance
    0.06
    _symbols
    0.06
    /calendar
    0.06
    alem
    0.06
     winters
    0.06
    quotes
    0.06
    ickou
    0.06
     snapshot
    0.06
    Act Density 0.006%

    No Known Activations