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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ecká
    -0.06
    セン
    -0.06
     Clarke
    -0.06
    識
    -0.06
     obsessed
    -0.06
    diamond
    -0.06
    sha
    -0.06
     detox
    -0.06
     Brett
    -0.05
     Москва
    -0.05
    POSITIVE LOGITS
    ?</
    0.07
     именно
    0.07
     selv
    0.07
     legally
    0.07
     tỷ
    0.07
     글
    0.06
     reflux
    0.06
    uspend
    0.06
    answers
    0.06
     Záp
    0.06
    Act Density 0.005%

    No Known Activations