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

    Neuronpedia

    INDEX
    Explanations

    Update

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gob
    -0.07
     consent
    -0.07
    struments
    -0.07
    877
    -0.07
     cos
    -0.07
     Phys
    -0.07
     beh
    -0.06
    660
    -0.06
     Gibbs
    -0.06
    host
    -0.06
    POSITIVE LOGITS
     update
    0.15
     Update
    0.13
    Update
    0.12
    update
    0.12
    UPDATE
    0.11
     updates
    0.10
    .update
    0.10
    Updates
    0.10
    (update
    0.09
    Updated
    0.09
    Act Density 0.038%

    No Known Activations