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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -compose
    -0.06
     defa
    -0.06
     DA
    -0.06
     Прот
    -0.06
     Микола
    -0.06
    していた
    -0.06
    )])
    -0.06
    광역시
    -0.06
     budouc
    -0.06
     establishes
    -0.06
    POSITIVE LOGITS
    รง
    0.07
     BMW
    0.06
     Indeed
    0.06
    valu
    0.06
    çi
    0.06
    Spell
    0.06
     noss
    0.06
     Fowler
    0.06
     pagamento
    0.06
    BMW
    0.06
    Act Density 0.000%

    No Known Activations