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

    Neuronpedia

    INDEX
    Explanations

    degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getProject
    -0.07
    -DD
    -0.07
    publication
    -0.06
    _AB
    -0.06
     Carmen
    -0.06
     �
    -0.06
     camino
    -0.06
    ินเด
    -0.06
     spider
    -0.06
     patriot
    -0.06
    POSITIVE LOGITS
     площад
    0.07
    _blueprint
    0.07
     guts
    0.06
    .
↵↵
    0.06
    ound
    0.06
     []
    0.06
    pesan
    0.06
    _queryset
    0.06
    lad
    0.06
    ">

↵
    0.06
    Act Density 0.002%

    No Known Activations