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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _only
    -0.07
     wäre
    -0.07
     сад
    -0.07
     mand
    -0.07
    düm
    -0.07
     morning
    -0.06
    olia
    -0.06
     اعمال
    -0.06
     Maz
    -0.06
    conf
    -0.06
    POSITIVE LOGITS
     böylece
    0.07
    ＼＼
    0.07
    -cigarettes
    0.07
    -----------*/↵
    0.06
     sınav
    0.06
    //!↵
    0.06
     คาส
    0.06
    Published
    0.06
     Escorts
    0.06
    =localhost
    0.06
    Act Density 0.001%

    No Known Activations