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

    Neuronpedia

    INDEX
    Explanations

    Various contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Observer
    -0.07
     macro
    -0.07
     Opens
    -0.06
     prints
    -0.06
     sufficiently
    -0.06
     Alexandre
    -0.06
     Save
    -0.06
    	render
    -0.06
     party
    -0.06
    tones
    -0.06
    POSITIVE LOGITS
     ακό
    0.07
    itbart
    0.06
    \Auth
    0.06
    doubleValue
    0.06
     </>↵
    0.06
    verbatim
    0.06
     وی
    0.06
    NotBlank
    0.06
     평당
    0.06
    Ka
    0.06
    Act Density 0.100%

    No Known Activations