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

    Neuronpedia

    INDEX
    Explanations

    Code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tolua
    -0.07
    <System
    -0.07
    .testing
    -0.07
     unnecessarily
    -0.06
     undergoing
    -0.06
    限期
    -0.06
    anych
    -0.06
    agma
    -0.06
    ⌺
    -0.06
     RouterModule
    -0.06
    POSITIVE LOGITS
    Cas
    0.08
    COL
    0.07
    »↵↵
    0.07
    Cars
    0.07
    _Device
    0.07
     settings
    0.06
     ,
↵
    0.06
    explicit
    0.06
    CAT
    0.06
    绿茶
    0.06
    Act Density 0.210%

    No Known Activations