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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Folk
    -0.07
     Tropical
    -0.07
     Integer
    -0.07
    ruits
    -0.07
     Sher
    -0.07
     Marr
    -0.07
    .players
    -0.07
    twitter
    -0.07
    Tweet
    -0.07
    沐
    -0.07
    POSITIVE LOGITS
     penetrate
    0.07
     cortisol
    0.07
    其次
    0.07
    NSURL
    0.07
    榰
    0.07
    �
    0.07
    뵈
    0.06
    התחלה
    0.06
     omdat
    0.06
    いると
    0.06
    Act Density 0.003%

    No Known Activations