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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、い
    -0.07
    ियम
    -0.06
    िश
    -0.06
    .Normal
    -0.06
     тогда
    -0.06
    ś
    -0.06
    새
    -0.06
    泡
    -0.06
     attent
    -0.06
     MESSAGE
    -0.06
    POSITIVE LOGITS
    semester
    0.07
    Titles
    0.07
    !/
    0.07
     Cover
    0.06
    меть
    0.06
    召
    0.06
    idity
    0.06
    ages
    0.06
    	DWORD
    0.06
    .catch
    0.06
    Act Density 0.135%

    No Known Activations