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

    Neuronpedia

    INDEX
    Explanations

    exploring various topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getState
    -0.07
    增加
    -0.07
     Россия
    -0.07
    LiveData
    -0.06
    510
    -0.06
    Parm
    -0.06
     becer
    -0.06
    [Test
    -0.06
     найб
    -0.06
    onta
    -0.06
    POSITIVE LOGITS
     apparently
    0.06
    <ll
    0.06
     있는데
    0.06
     antic
    0.06
     unspecified
    0.06
    rvine
    0.06
    Thank
    0.06
    -marker
    0.06
    вай
    0.06
     intervened
    0.06
    Act Density 0.083%

    No Known Activations