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

    Neuronpedia

    INDEX
    Explanations

    X

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menj
    -0.08
     внешне
    -0.08
    _ij
    -0.07
     ValidationError
    -0.07
    �
    -0.07
    ⏎
    -0.07
     applicationWill
    -0.07
     fortunate
    -0.07
    꺳
    -0.06
     ])
    -0.06
    POSITIVE LOGITS
    と思う
    0.08
    _REST
    0.08
    拘
    0.07
     fifo
    0.07
    绑架
    0.07
     Office
    0.07
     ATF
    0.07
     guts
    0.07
     arrest
    0.07
    Disallow
    0.07
    Act Density 0.000%

    No Known Activations