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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alloc
    -0.07
     women
    -0.06
    CONFIG
    -0.06
     עמוק
    -0.06
     shooters
    -0.06
     �
    -0.06
     moms
    -0.06
    凇
    -0.06
    Dest
    -0.06
     nh
    -0.06
    POSITIVE LOGITS
    进行全面
    0.07
     qualità
    0.07
     (>
    0.07
     Lime
    0.07
    Courses
    0.07
    管线
    0.06
    测算
    0.06
     roma
    0.06
    新版
    0.06
    .ylim
    0.06
    Act Density 0.114%

    No Known Activations