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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,temp
    -0.07
    Autowired
    -0.07
     offerings
    -0.06
     franch
    -0.06
     Families
    -0.06
     Stay
    -0.06
    ymce
    -0.06
    ,Q
    -0.06
    identified
    -0.06
     Inv
    -0.06
    POSITIVE LOGITS
     सज
    0.06
    ~↵
    0.06
    _i
    0.06
    ".↵
    0.06
    "↵
    0.06
     APC
    0.06
     втор
    0.06
     electronically
    0.06
    нул
    0.06
    };
↵
↵
    0.06
    Act Density 0.090%

    No Known Activations