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

    Neuronpedia

    INDEX
    Explanations

    sinking or setting origins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CppCodeGen
    -0.79
    djangoproject
    -0.78
     committed
    -0.77
    rivit
    -0.74
     sank
    -0.72
     sunk
    -0.70
    CloseOperation
    -0.70
    Since
    -0.69
     Committed
    -0.68
     sink
    -0.67
    POSITIVE LOGITS
     then
    0.64
    IContainer
    0.62
     the
    0.59
     
    0.55
    اً
    0.53
     simplest
    0.53
     its
    0.50
     briefly
    0.49
     next
    0.48
     several
    0.47
    Act Density 0.071%

    No Known Activations