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

    Neuronpedia

    INDEX
    Explanations

    Asking questions/requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boasted
    -0.07
    imizer
    -0.06
    urances
    -0.06
    Latest
    -0.06
     NEG
    -0.06
    USR
    -0.06
    -standard
    -0.06
     آیا
    -0.05
    textTheme
    -0.05
    .Private
    -0.05
    POSITIVE LOGITS
     ErrorHandler
    0.07
     disdain
    0.07
    .Endpoint
    0.07
     Instruction
    0.06
    ANNOT
    0.06
     lakh
    0.06
    had
    0.06
    �
    0.06
     salesman
    0.06
    (coll
    0.06
    Act Density 0.001%

    No Known Activations