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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hag
    -0.08
    般
    -0.07
     яка
    -0.06
    Connor
    -0.06
    .integration
    -0.06
    ское
    -0.06
    Graph
    -0.06
    .cfg
    -0.06
    cad
    -0.06
    πλ
    -0.06
    POSITIVE LOGITS
     unten
    0.07
     overridden
    0.07
    ActivityResult
    0.07
    )obj
    0.06
     launder
    0.06
    .avi
    0.06
    ercial
    0.06
    hits
    0.06
     learnt
    0.06
     prohibits
    0.06
    Act Density 0.021%

    No Known Activations