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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     favourites
    -0.07
    istance
    -0.07
    Dismiss
    -0.06
     Variety
    -0.06
    bo
    -0.06
     pending
    -0.06
     보내
    -0.06
     customers
    -0.06
    string
    -0.06
    .String
    -0.06
    POSITIVE LOGITS
     البته
    0.07
     hallway
    0.07
    èles
    0.06
     tissue
    0.06
     Рус
    0.06
    /**
↵
    0.06
     doit
    0.06
    |[
    0.06
    ToOne
    0.06
     HOWEVER
    0.05
    Act Density 0.016%

    No Known Activations