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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thương
    -0.07
    xeb
    -0.07
    aná
    -0.07
    мар
    -0.07
    џN
    -0.07
    chas
    -0.06
    	pr
    -0.06
    okud
    -0.06
     Marlins
    -0.06
    warehouse
    -0.06
    POSITIVE LOGITS
     ability
    0.07
     exceptionally
    0.07
     accounting
    0.07
    Buffer
    0.07
     Percentage
    0.06
     vacuum
    0.06
     additionally
    0.06
    <vector
    0.06
     информации
    0.06
    (atom
    0.06
    Act Density 0.004%

    No Known Activations