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

    Neuronpedia

    INDEX
    Explanations

    vm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cog
    -0.08
    #g
    -0.07
     shoved
    -0.07
     تعد
    -0.07
    �
    -0.07
     (:
    -0.07
    :[],↵
    -0.07
     attaches
    -0.07
     Für
    -0.06
     plunge
    -0.06
    POSITIVE LOGITS
    三十年
    0.07
     lagi
    0.07
    sampling
    0.07
    עמוד
    0.07
     Burnett
    0.07
    憋
    0.07
    .To
    0.07
    מלחמה
    0.07
    觟
    0.06
    =post
    0.06
    Act Density 0.003%

    No Known Activations