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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    说到这里
    -0.08
    笛
    -0.08
    中关村
    -0.07
     [<
    -0.07
     illustration
    -0.07
    lash
    -0.07
    ண
    -0.07
     wandering
    -0.07
    絜
    -0.07
    .ibatis
    -0.06
    POSITIVE LOGITS
            ↵        ↵
    0.08
    阻
    0.08
     flo
    0.07
    cont
    0.07
    	File
    0.07
    UFACT
    0.07
    *
    0.07
                                ↵
    0.07
     Court
    0.07
    Resource
    0.07
    Act Density 0.124%

    No Known Activations