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

    Neuronpedia

    INDEX
    Explanations

    login or save content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parchment
    -0.08
    检察
    -0.07
    irut
    -0.07
     parachute
    -0.07
    瑧
    -0.07
     caut
    -0.07
     Ethiopian
    -0.07
    חוף
    -0.07
     chambre
    -0.07
    ዩ
    -0.07
    POSITIVE LOGITS
     Di
    0.08
    覆盖
    0.08
     reimb
    0.07
    contr
    0.07
     Musk
    0.07
    MSC
    0.07
     '''↵
    0.07
     
↵ 
↵
    0.07
     sw
    0.07
     Mi
    0.07
    Act Density 0.003%

    No Known Activations