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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indle
    -0.07
     FEATURES
    -0.07
     disrespectful
    -0.07
     Boo
    -0.06
     otras
    -0.06
    rove
    -0.06
    mani
    -0.06
     "=
    -0.06
    oper
    -0.06
    ící
    -0.06
    POSITIVE LOGITS
    itemId
    0.07
     Push
    0.06
    redict
    0.06
    .className
    0.06
    #endregion
    0.06
    ams
    0.06
    favorites
    0.06
    '=>$
    0.06
    �始化
    0.06
    \r
    0.06
    Act Density 0.089%

    No Known Activations