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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TemplateName
    -0.06
    _AFTER
    -0.06
    _domains
    -0.06
     �
    -0.06
    .eval
    -0.06
     Jim
    -0.06
    -Co
    -0.06
    awaiter
    -0.06
    Forever
    -0.06
    _Pods
    -0.06
    POSITIVE LOGITS
    件
    0.07
    LINK
    0.06
     修改
    0.06
     rozhodnutí
    0.06
     cis
    0.06
     《
    0.06
     misc
    0.06
     лит
    0.06
     interfaces
    0.06
     paired
    0.06
    Act Density 0.014%

    No Known Activations