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

    Neuronpedia

    INDEX
    Explanations

    General conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mild
    -0.07
     Harmony
    -0.07
    Run
    -0.07
    Define
    -0.06
     bel
    -0.06
     Changed
    -0.06
     Rope
    -0.06
     Hedge
    -0.06
    Import
    -0.06
    _urls
    -0.06
    POSITIVE LOGITS
    怎么
    0.07
     threadIdx
    0.06
    CK
    0.06
    урс
    0.06
     está
    0.06
    Autowired
    0.06
    	false
    0.06
    Footer
    0.06
    Prot
    0.06
     предус
    0.06
    Act Density 0.000%

    No Known Activations