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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    れた
    -0.07
    なく
    -0.06
     작업
    -0.06
     elkaar
    -0.06
    λια
    -0.06
    wal
    -0.06
     ViewController
    -0.06
    徒歩
    -0.06
    泊
    -0.06
    INavigationController
    -0.06
    POSITIVE LOGITS
     dime
    0.06
     Russ
    0.06
    Mil
    0.06
    )*
    0.06
    GreaterThan
    0.06
     poorer
    0.06
     अगल
    0.06
    raise
    0.06
    .street
    0.06
     vog
    0.05
    Act Density 0.026%

    No Known Activations