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

    Neuronpedia

    INDEX
    Explanations

    Processes and steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reminder
    -0.08
     condition
    -0.06
    "A
    -0.06
    lost
    -0.06
     wing
    -0.06
    inois
    -0.06
     plane
    -0.06
    	fill
    -0.06
    carbon
    -0.06
    dependency
    -0.06
    POSITIVE LOGITS
     efekt
    0.07
    celain
    0.07
     많이
    0.07
     впол
    0.06
     vara
    0.06
    [:-
    0.06
     �
    0.06
     sociale
    0.06
    鉄
    0.06
     payable
    0.06
    Act Density 0.029%

    No Known Activations