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

    Neuronpedia

    INDEX
    Explanations

    Conversational/Dialogue text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اللغة
    -0.06
     zm
    -0.06
     prisons
    -0.06
     contract
    -0.06
     AFC
    -0.06
    .INVISIBLE
    -0.06
    败
    -0.05
    compat
    -0.05
     explanation
    -0.05
     iss
    -0.05
    POSITIVE LOGITS
    шего
    0.06
    OfType
    0.06
     BASE
    0.06
     llvm
    0.06
     serializer
    0.06
     mö
    0.06
    าหล
    0.06
     celebrates
    0.06
     addChild
    0.06
    THEN
    0.06
    Act Density 0.009%

    No Known Activations