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

    Neuronpedia

    INDEX
    Explanations

    examinations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NH
    -0.07
     Nothing
    -0.06
     Navigation
    -0.06
    ･･
    -0.06
    也没有
    -0.06
    aight
    -0.06
     »↵↵
    -0.06
    atives
    -0.06
    .extensions
    -0.06
     Beach
    -0.06
    POSITIVE LOGITS
     mogła
    0.08
    峰值
    0.07
    ismet
    0.07
    imiters
    0.07
     disposing
    0.06
    ց
    0.06
    scheduled
    0.06
    	va
    0.06
     slopes
    0.06
     gc
    0.06
    Act Density 0.031%

    No Known Activations