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

    Neuronpedia

    INDEX
    Explanations

    bi or microbi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ッシュ
    -0.07
     karma
    -0.07
     anim
    -0.06
     setContent
    -0.06
     algumas
    -0.06
     dừng
    -0.06
     ellas
    -0.06
     Barker
    -0.06
    řes
    -0.06
    기간
    -0.06
    POSITIVE LOGITS
     facade
    0.06
     Влади
    0.06
    olog
    0.06
    ponsor
    0.06
    authority
    0.06
     Integration
    0.06
    ,t
    0.06
    _DRIVER
    0.06
    说明
    0.05
     Plant
    0.05
    Act Density 0.003%

    No Known Activations