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

    Neuronpedia

    INDEX
    Explanations

    bond

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Room
    -0.06
    _https
    -0.06
    ASCII
    -0.06
    زا
    -0.06
    寒
    -0.06
    Capture
    -0.06
    IDD
    -0.06
    .Criteria
    -0.06
    �
    -0.06
     Chunk
    -0.06
    POSITIVE LOGITS
    -blog
    0.07
     lit
    0.06
    .Unlock
    0.06
    .setType
    0.06
     Lt
    0.06
     lightly
    0.06
     asla
    0.06
    ,[
    0.06
     Modeling
    0.06
    _SCL
    0.06
    Act Density 0.006%

    No Known Activations