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

    Neuronpedia

    INDEX
    Explanations

    similarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McCabe
    -0.06
     　 　 　
    -0.06
     staffers
    -0.06
     Αυ
    -0.06
     Option
    -0.06
     Αθή
    -0.06
    abet
    -0.06
     bluff
    -0.06
     Каб
    -0.06
    .JScrollPane
    -0.06
    POSITIVE LOGITS
     deaths
    0.07
     gown
    0.07
    .surname
    0.07
    /dataTables
    0.06
    عن
    0.06
     solo
    0.06
    MODEL
    0.06
    ($)
    0.06
    を見
    0.06
    .tolist
    0.06
    Act Density 0.024%

    No Known Activations