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

    Neuronpedia

    INDEX
    Explanations

    ISP

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provides
    -0.07
     pci
    -0.07
    :")↵
    -0.07
     zoo
    -0.07
     perché
    -0.07
     GetAll
    -0.07
    _WRITE
    -0.06
     Gn
    -0.06
     glorious
    -0.06
     minus
    -0.06
    POSITIVE LOGITS
     Ownership
    0.08
    农副产品
    0.07
    肃
    0.07
    โบราณ
    0.07
     Cosby
    0.07
    wendung
    0.07
    .abstract
    0.07
    中国人民
    0.07
     обор
    0.06
     Hover
    0.06
    Act Density 0.000%

    No Known Activations