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

    Neuronpedia

    INDEX
    Explanations

    a variety of function words like prepositions articles conjunctions often preceding nouns

    oai_token-act-pair · gemini-2.0-flash

    routes and paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lines
    -1.23
     LINES
    -1.13
     routes
    -1.13
     Paths
    -1.09
     Roads
    -1.08
    Lines
    -1.07
     Routes
    -1.07
     lines
    -1.06
    routes
    -1.05
     paths
    -1.05
    POSITIVE LOGITS
    Autoritní
    0.66
     estekak
    0.65
    发表于
    0.60
    NUMX
    0.59
    المناصب
    0.58
    apunov
    0.54
    verifyException
    0.54
    ModelSerializer
    0.53
     myſelf
    0.51
    ViewChild
    0.50
    Act Density 5.844%

    No Known Activations