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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]]↵↵
    -0.06
     Spa
    -0.06
    }/>↵
    -0.06
     врач
    -0.06
    ###↵↵
    -0.06
    '),↵↵
    -0.06
    "];
↵
    -0.06
    "
↵
↵
    -0.06
        	
↵
    -0.06
    ")},↵
    -0.06
    POSITIVE LOGITS
    utral
    0.07
     footwear
    0.07
     sooner
    0.06
    blank
    0.06
     harmed
    0.06
     hurricanes
    0.06
    19
    0.06
     circumstances
    0.06
    aser
    0.06
    AGO
    0.06
    Act Density 0.000%

    No Known Activations