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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sasha
    -0.07
    _CONTACT
    -0.07
    	fwrite
    -0.07
    nim
    -0.06
     denne
    -0.06
    isAdmin
    -0.06
     inne
    -0.06
    /server
    -0.06
    φο
    -0.06
    -third
    -0.06
    POSITIVE LOGITS
    俄
    0.07
     tur
    0.06
     чемпион
    0.06
    _pool
    0.06
    	help
    0.06
    (create
    0.06
     Hydro
    0.06
     doll
    0.06
     Looking
    0.06
     Suppose
    0.06
    Act Density 0.013%

    No Known Activations