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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deflect
    -0.08
     Arrival
    -0.07
    	ok
    -0.07
     CORE
    -0.07
     Nim
    -0.07
     arrival
    -0.07
    oo
    -0.06
     singleton
    -0.06
     Planning
    -0.06
     Snake
    -0.06
    POSITIVE LOGITS
     Acad
    0.07
    �
    0.07
     candies
    0.06
    cit
    0.06
    énom
    0.06
    Proceed
    0.06
    AGES
    0.06
    published
    0.06
    trad
    0.06
    assing
    0.06
    Act Density 0.004%

    No Known Activations