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

    Neuronpedia

    INDEX
    Explanations

    ised

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ByKey
    -0.08
     checklist
    -0.07
     Hệ
    -0.07
    이며
    -0.06
    üsseldorf
    -0.06
     UnityEngine
    -0.06
     Mistress
    -0.06
     disobed
    -0.06
     councillors
    -0.06
    .VideoCapture
    -0.06
    POSITIVE LOGITS
     [].
    0.07
     ас
    0.07
     obsessed
    0.06
    [train
    0.06
     Universidad
    0.06
    מ
    0.06
     三
    0.06
    _panel
    0.06
    [this
    0.06
     ){↵↵
    0.06
    Act Density 0.003%

    No Known Activations