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

    Neuronpedia

    INDEX
    Explanations

    Hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drilled
    -0.07
    serv
    -0.06
    dados
    -0.06
    licting
    -0.06
    (predict
    -0.06
    _rest
    -0.06
     Announcement
    -0.06
     triumph
    -0.06
     Tibet
    -0.06
    ของค
    -0.06
    POSITIVE LOGITS
     사망
    0.06
     Gaz
    0.06
    �
    0.06
     OSP
    0.06
     hotels
    0.06
    _TX
    0.06
    ющей
    0.06
     Even
    0.06
    万元
    0.06
    -analysis
    0.06
    Act Density 0.001%

    No Known Activations