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

    Neuronpedia

    INDEX
    Explanations

    scientific names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    configs
    -0.07
    _PKT
    -0.07
     redistributed
    -0.07
     unmist
    -0.06
    .disabled
    -0.06
    arhus
    -0.06
     Baghd
    -0.06
     statusBar
    -0.06
     chipset
    -0.06
    leston
    -0.06
    POSITIVE LOGITS
     predicate
    0.07
     {↵
    0.07
     sanit
    0.06
    ++++++++++++++++
    0.06
    是我
    0.06
    _rep
    0.06
    《
    0.06
    .="
    0.06
    _preference
    0.06
     речов
    0.06
    Act Density 0.018%

    No Known Activations