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

    Neuronpedia

    INDEX
    Explanations

    exercises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laptop
    -0.07
    	P
    -0.06
    ]:↵
    -0.06
    _DONE
    -0.06
     Words
    -0.06
     ن
    -0.06
     simp
    -0.06
    아요
    -0.06
    alone
    -0.06
     Fo
    -0.05
    POSITIVE LOGITS
    iven
    0.07
     reconstruct
    0.07
    лов
    0.07
    ixo
    0.07
     Volunteers
    0.06
     statistically
    0.06
     کشورهای
    0.06
    さらに
    0.06
    äh
    0.06
    getManager
    0.06
    Act Density 0.026%

    No Known Activations