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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tal
    -0.07
     těchto
    -0.07
     SMP
    -0.07
     scouts
    -0.06
     Gaines
    -0.06
    Jerry
    -0.06
    	vector
    -0.06
     Dil
    -0.06
     Ingram
    -0.06
     },↵↵↵
    -0.06
    POSITIVE LOGITS
    로나
    0.07
    戶
    0.07
    ?<
    0.07
    (TestCase
    0.06
     Slip
    0.06
     말씀
    0.06
     ={↵
    0.06
    rosso
    0.06
     Downloads
    0.06
     시
    0.06
    Act Density 0.035%

    No Known Activations