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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Selenium
    -0.08
    纽带
    -0.07
    ws
    -0.07
    .pp
    -0.07
     alias
    -0.07
    urement
    -0.07
    ility
    -0.07
    -testid
    -0.07
     faction
    -0.06
     pipelines
    -0.06
    POSITIVE LOGITS
     blazing
    0.07
     originated
    0.07
     debut
    0.07
    椹
    0.07
     originate
    0.07
     schöne
    0.07
    奇怪
    0.07
     Emotional
    0.07
     incor
    0.07
     REALLY
    0.06
    Act Density 0.031%

    No Known Activations