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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Baylor
    -0.07
     Velvet
    -0.07
     Springer
    -0.06
    listeners
    -0.06
     Mechan
    -0.06
    .TableName
    -0.06
     Burr
    -0.06
     chir
    -0.06
    .add
    -0.06
     wider
    -0.06
    POSITIVE LOGITS
     öt
    0.06
    Luckily
    0.06
     بيانات
    0.06
     owed
    0.06
     refunds
    0.06
    GP
    0.06
     użytk
    0.06
    violent
    0.06
    jan
    0.06
    字幕
    0.06
    Act Density 0.052%

    No Known Activations