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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    egin
    -0.07
     外
    -0.07
    data
    -0.07
    外
    -0.07
    OUNCE
    -0.07
     minced
    -0.07
     Harold
    -0.07
     queen
    -0.06
     GEN
    -0.06
     temperatura
    -0.06
    POSITIVE LOGITS
    _compute
    0.06
    _ALLOWED
    0.06
    (r
    0.06
    Pipe
    0.06
    ilation
    0.06
     chtě
    0.06
     maxY
    0.06
    HTTPRequest
    0.06
    ');");↵
    0.06
    _MODE
    0.06
    Act Density 0.048%

    No Known Activations