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

    Neuronpedia

    INDEX
    Explanations

    guess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     публі
    -0.07
    ера
    -0.07
    	port
    -0.07
     TECHNO
    -0.07
     manten
    -0.07
     Royal
    -0.07
     Salad
    -0.06
     Fot
    -0.06
     Dol
    -0.06
     Vert
    -0.06
    POSITIVE LOGITS
     guess
    0.09
     guessed
    0.09
     guessing
    0.08
     guesses
    0.08
    ิญ
    0.07
     Guess
    0.07
    guess
    0.07
    Guess
    0.07
    pillar
    0.06
    -watch
    0.06
    Act Density 0.008%

    No Known Activations