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

    Neuronpedia

    INDEX
    Explanations

    experimental setups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     epoch
    -0.07
     tre
    -0.06
    -0.06
     preventive
    -0.06
     empathy
    -0.06
    杜
    -0.06
    uploads
    -0.06
    зем
    -0.06
    other
    -0.06
    „
    -0.06
    POSITIVE LOGITS
     exhilar
    0.06
    밍
    0.06
     віт
    0.06
     istediğiniz
    0.06
    Hierarchy
    0.06
     CSI
    0.06
     usuarios
    0.06
    liche
    0.06
     만족
    0.06
     Reflect
    0.06
    Act Density 0.047%

    No Known Activations