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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unity
    -0.07
     moral
    -0.07
     kariy
    -0.06
     chẳng
    -0.06
    яття
    -0.06
    argo
    -0.06
    -destruct
    -0.06
     uniformly
    -0.06
     مکان
    -0.06
     Tento
    -0.06
    POSITIVE LOGITS
     before
    0.08
    Before
    0.08
     Before
    0.08
    before
    0.07
     carved
    0.06
    OUS
    0.06
    quences
    0.06
     окон
    0.06
    .after
    0.06
    979
    0.06
    Act Density 0.024%

    No Known Activations