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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     daar
    -0.07
     summon
    -0.07
     会
    -0.07
    .Produ
    -0.07
     guitarist
    -0.06
     หร
    -0.06
     electron
    -0.06
     öğ
    -0.06
     لها
    -0.06
     allot
    -0.06
    POSITIVE LOGITS
     buried
    0.06
    :
    0.06
     Conn
    0.06
     campaigns
    0.06
    盗
    0.06
     conta
    0.06
     Nos
    0.05
     BadRequest
    0.05
     Caller
    0.05
     pirates
    0.05
    Act Density 0.000%

    No Known Activations