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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    List
    -0.07
     responds
    -0.07
     aerial
    -0.06
     Diamonds
    -0.06
    	fields
    -0.06
    665
    -0.06
    Command
    -0.06
     grounds
    -0.06
    =False
    -0.06
    (Guid
    -0.06
    POSITIVE LOGITS
    .opt
    0.07
     pří
    0.06
    ustral
    0.06
     nós
    0.06
     Finding
    0.06
     adventurer
    0.06
    PASS
    0.06
     Birleşik
    0.06
     ninh
    0.06
     startups
    0.06
    Act Density 0.050%

    No Known Activations