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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rookies
    -0.07
    (height
    -0.07
     MODIFY
    -0.06
    瓜
    -0.06
     descon
    -0.06
    OfDay
    -0.06
    866
    -0.06
     increasingly
    -0.06
     preach
    -0.06
    eliness
    -0.06
    POSITIVE LOGITS
    ]};↵
    0.07
    _",
    0.06
    ถม
    0.06
     TCL
    0.06
     baff
    0.06
    fic
    0.06
    Ross
    0.06
     dile
    0.06
    _cases
    0.06
     trợ
    0.06
    Act Density 0.141%

    No Known Activations