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

    Neuronpedia

    INDEX
    Explanations

    XML headers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zi
    -0.07
     accidentally
    -0.06
    ritel
    -0.06
    IGH
    -0.06
     Seconds
    -0.06
    стал
    -0.06
     closet
    -0.06
     BTS
    -0.06
    imbabwe
    -0.06
     ALIGN
    -0.06
    POSITIVE LOGITS
    跨
    0.07
    科研
    0.07
    _transfer
    0.07
    月
    0.07
    គ
    0.07
    你的
    0.07
    -IS
    0.07
    Know
    0.07
     />
↵
    0.07
    _instance
    0.06
    Act Density 0.001%

    No Known Activations