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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Size
    -0.07
     latitude
    -0.07
     warn
    -0.07
     "."
    -0.07
    :.:.:
    -0.07
    	diff
    -0.07
    valid
    -0.06
     Brad
    -0.06
     Dependencies
    -0.06
     water
    -0.06
    POSITIVE LOGITS
    }";↵
    0.07
    ourced
    0.07
     Chile
    0.07
    )d
    0.07
    ุง
    0.06
    Declared
    0.06
     politic
    0.06
    タ
    0.06
     청
    0.06
    .weapon
    0.06
    Act Density 0.010%

    No Known Activations