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

    Neuronpedia

    INDEX
    Explanations

    Chinese/Korean characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fu
    -0.07
    Access
    -0.06
    ниці
    -0.06
    스로
    -0.06
    _perm
    -0.06
     transformative
    -0.06
    行动
    -0.06
    _z
    -0.06
     mediated
    -0.06
     би
    -0.06
    POSITIVE LOGITS
    .Annotation
    0.08
    特
    0.08
    .metamodel
    0.07
    ْل
    0.06
    PERT
    0.06
    .TYPE
    0.06
     //</
    0.06
     کال
    0.06
    (?:
    0.06
     ticker
    0.06
    Act Density 0.003%

    No Known Activations