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

    Neuronpedia

    INDEX
    Explanations

    describing something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carcin
    -0.07
     '[
    -0.07
     ECS
    -0.07
     zab
    -0.07
    aporan
    -0.06
    allet
    -0.06
     Pessoa
    -0.06
    -pe
    -0.06
     νε
    -0.06
    _simps
    -0.06
    POSITIVE LOGITS
     şeyi
    0.07
     Barclays
    0.07
     dynamically
    0.06
    ेड
    0.06
    Samsung
    0.06
    _Cl
    0.06
     Boxing
    0.06
    	parse
    0.06
     analiz
    0.06
     comb
    0.06
    Act Density 0.042%

    No Known Activations