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

    Neuronpedia

    INDEX
    Explanations

    Influencing factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -bl
    -0.07
    ункци
    -0.07
    hana
    -0.07
    ौत
    -0.07
     Modify
    -0.06
    ather
    -0.06
    .patch
    -0.06
     Late
    -0.06
    灵
    -0.06
    _SERVER
    -0.06
    POSITIVE LOGITS
    --
↵
    0.06
     склада
    0.06
    399
    0.06
    /images
    0.06
    	
↵	
↵
    0.06
    .*,
    0.06
    draft
    0.06
    mos
    0.06
     ]↵↵↵
    0.06
    folders
    0.06
    Act Density 0.061%

    No Known Activations