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

    Neuronpedia

    INDEX
    Explanations

    arguments/parameters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    博士学位
    -0.08
    咉
    -0.07
     simple
    -0.07
    =pk
    -0.07
     coins
    -0.07
     identified
    -0.07
     banner
    -0.07
    ᠠ
    -0.07
     rocks
    -0.06
    微型
    -0.06
    POSITIVE LOGITS
    olis
    0.08
    'n
    0.08
    woods
    0.07
     ngừa
    0.07
    рабат
    0.07
    אית
    0.07
    Ngu
    0.07
    OAD
    0.07
    olicit
    0.07
     Vaccine
    0.07
    Act Density 0.044%

    No Known Activations