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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fayd
    -0.07
    Twenty
    -0.06
    plers
    -0.06
    iltro
    -0.06
     Twenty
    -0.06
    Ch
    -0.06
    ách
    -0.06
    ›
    -0.06
    -flat
    -0.06
     az
    -0.05
    POSITIVE LOGITS
    οντας
    0.07
     realloc
    0.07
    	inst
    0.07
    ฤ
    0.07
    (dateTime
    0.07
    COOKIE
    0.07
     Aires
    0.07
     protagonists
    0.06
     constructors
    0.06
     contenders
    0.06
    Act Density 0.058%

    No Known Activations