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

    Neuronpedia

    INDEX
    Explanations

    oxid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aign
    -0.07
     male
    -0.06
    _cmd
    -0.06
    „
    -0.06
    	menu
    -0.06
     jaar
    -0.06
     exempt
    -0.06
     tls
    -0.06
    athe
    -0.06
    *r
    -0.06
    POSITIVE LOGITS
    .damage
    0.07
    Refs
    0.06
     задов
    0.06
    .rdf
    0.06
    /resources
    0.06
     proti
    0.06
    _Desc
    0.06
     tốc
    0.06
     liability
    0.06
    _WATER
    0.06
    Act Density 0.003%

    No Known Activations