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

    Neuronpedia

    INDEX
    Explanations

    exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     merc
    -0.07
    	graph
    -0.07
    _GET
    -0.06
    (site
    -0.06
    ┐
    -0.06
     profes
    -0.06
    ORT
    -0.06
    ặc
    -0.06
     dlouhodob
    -0.06
    	old
    -0.06
    POSITIVE LOGITS
    OH
    0.06
     FIL
    0.06
     nei
    0.06
    Little
    0.06
     discrete
    0.06
     packed
    0.06
     nah
    0.06
     Kol
    0.06
     �
    0.06
    .tem
    0.06
    Act Density 0.001%

    No Known Activations