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

    Neuronpedia

    INDEX
    Explanations

    code/technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ExecuteReader
    -0.65
    featureID
    -0.59
    ParallelGroup
    -0.57
    ImageContext
    -0.56
    RUnlock
    -0.55
    createNewFile
    -0.54
    BarStyle
    -0.53
    moveToFirst
    -0.52
    autant
    -0.52
    ATOM
    -0.52
    POSITIVE LOGITS
     oprot
    0.50
     invokingState
    0.48
     GenerationType
    0.47
    mgren
    0.46
     Himo
    0.45
    ngdoc
    0.45
    PrivateRoute
    0.43
     beira
    0.43
    ">//
    0.43
     ters
    0.42
    Act Density 0.000%

    No Known Activations