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

    Neuronpedia

    INDEX
    Explanations

    Code/Configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    woord
    -0.07
    颈椎
    -0.07
    (".")
    -0.07
    ,axis
    -0.07
     aconte
    -0.07
     опас
    -0.07
     Zucker
    -0.07
    📡
    -0.07
     PARK
    -0.07
     '--
    -0.07
    POSITIVE LOGITS
     Land
    0.07
    _left
    0.07
    -cn
    0.07
     daher
    0.07
    ред
    0.07
    #
    0.07
     Idea
    0.07
    jualan
    0.06
    movies
    0.06
    隺
    0.06
    Act Density 0.002%

    No Known Activations